NAV Navbar
python json

Introduction

This documentation focuses on describing our public API. You will find the full description and content of every object returned by the LETTRIA API.

Requests and authentication

To make a request using curl, replace API_KEY with your personal token
and YOUR_SENTENCE with the text to process :


curl -H "Authorization: LettriaProKey API_KEY" \
-H "Content-Type: application/json" \
-X POST "https://api.lettria.com/main" \
-d '{ "text" : "YOUR_SENTENCE" }'

All your requests must contain a header called Authorization. The value of the header must be created like so : "LettriaProKey API_KEY".

Get your free API_KEY on your Dashboard.

Python SDK

import lettria

nlp = lettria.NLP(api_key)
nlp.add_document([sentence_1, sentence_2])

for doc in nlp:
    for sentence in doc:
        print(sentence.token, sentence.pos)

To use our API, you will need a personal key, refered as API_KEY. Get your free API_KEY on your Dashboard.
Install using Python Software Developpement Kit :

pip install lettria

Check the official sources for more information and documentation on how to extract key informations using our SDK : https://github.com/Lettria/sdk-python

NLP class

NLP is a class designed to give access to relevant data at the different levels (document, sentence, subsentence) in an intuitive way. It allows to perform quick data exploration, manipulation and analysis.
It is also used to perform requests and can save and load the result as JSON objects.

When a response from the API is received it is stored in a hierarchy of classes:
NLP (all data) => Document => Sentence => Subsentence => Token
At each level direct access to inferior levels is possible i.e. nlp.sentences gives access to a list of all the Sentence in the current data, while nlp.documents[0].sentences gives only the Sentence of the first Document.

NLP is iterable and will yield Document instances.

Attributes / Properties

Name Type Description
documents list of Document instances List of all the Document instances.
sentences list of Sentence instances Direct access to all of the Sentences instances.
subsentences list of Subsentence instances Direct access to all of the Subsentence instances.
tokens list of Token instances Direct access to all Token in the subsentence
fields list of string List of all common properties accessible at all levels (token, pos etc.)
client instance of Client Client used for performing request to Lettria's API
Common properties depends on property Properties allowing access to specific data (pos, token etc.)

Methods

Data management

METHOD DESCRIPTION
add_document() Submits document to API
save_results() Saves data from json file
load_results() Loads data from json file
add_client() Adds new client / api_key

Analysis

METHOD DESCRIPTION
vocabulary() Returns vocabulary from current data.
word_count() Returns word count from current data.
word_frequency() Returns word frequency of current data.
list_entities() Returns dictionaries of detected entities by type.

add_document

add_document(document, skip_document = False, id=None)

Performs a request to lettria API using the API_KEY provided. Results are appended as an additional Document instance to the documents attribute.

Parameters:

Name Type Description Optional
document string or list of string Data to be sent to the API False
skip_document bool Whether to skip the document if there is a problem during processing True
id str Id to identify the document, by default an incrementing integer is assigned. True

save_results

save_results(file = '')

Writes current results to a JSON file. If no file is specified the default path is results_X.json with X being next 'free' integer.

Parameters:

Name Type Description Optional
file string Path of file to write in. True

load_results

load_results(path = 'results_0', reset = False)

Loads results from a JSON file.

Parameters:

Name Type Description Optional
file string Path of file to load. True
reset bool Whether to erase current data. True

add_client

add_client(client = None, api_key = None)

Replaces current client with provided one, or creates a new client using the provided api_key.

Parameters:

Name Type Description Optional
client instance of Client class Client instance to replace the current one. True
api_key string Key to use for the new client. True

Data analysis

vocabulary

vocabulary(filter_pos = None, lemma=False, level='global')

Returns vocabulary from current data with their associated POStag i.e. if a word appears both as a verb and a noun it will be in two tuples (word, 'V'), (word, 'N'). Allows filtering by POS tags.

Parameters:

Name Type Description Optional
filter_pos list of string Tags to use for filtering. True
level string Level of analysis, 'global' or 'document'. True
lemma string Whether to use lemma or plain words. True


Return:

Type Description
list of tuple List of unique tuples (token, POStag).

word_count

word_count(filter_pos = None, lemma=False, level='global'):

Returns count of words from current data with their associated POStag i.e. if a word appears both as a verb and a noun it will be in two tuples (word, 'V'), (word, 'N'). Allows filtering by POS tags.

Parameters:

Name Type Description Optional
filter_pos list of string Tags to use for filtering. True
level string Level of analysis, 'global' or 'document'. True
lemma string Whether to use lemma or plain words. True


Return:

Type Description
dictionary dictionary of word counts { (token, POStag): occurences }.

word_frequency

word_frequency(filter_pos = None, lemma=False, level='global')

Returns words or lemma frequency, allows filtering by POS tag

Parameters:

Name Type Description Optional
filter_pos list of string Tags to use for filtering. True
lemma bool Whether to use lemma or plain words. True
level string Level of analysis, 'global' or 'document'. True


Return:

Type Description
dictionary Dictionary of word frequency

list_entities

list_entities(level='global')

Returns dictionaries of detected entities by type.

Parameters:

Name Type Description Optional
level string Level of analysis, 'global', 'document', 'sentence', 'subsentence'. True

Return:

Type Description
list of dictionary List of dictionaries of different entities at the specified level.

Document Class

Document stores the information for a document (for example an online review for a product or a news article). The class is iterable and will yield instances of Sentence.

Attributes / Properties

Name Type Description
sentences list of Sentence instances List of Sentences of the document.
subsentences list of Subsentence instances Direct access to list of Subsentence for the document.
id str Id of document, by default sequential integer if not provided.
common properties depends on property Properties allowing access to specific data (pos, token etc.).

Sentence Class

Sentence stores data for a sentence. Sentences are delimited automatically from the input raw text. For longer and more complicated sentences it can be advantageous to further cut the sentences into subsentences.

Sentence is iterable and will yield instances of Token class

Attributes / Properties

Name Type Description
subsentences list of Subsentence instances List of Subsentence in the sentence
tokens list of Token instances List of Token in the sentence
common properties depends on property Properties allowing access to specific data (pos, token etc.)

Subsentence Class

Subsentence stores data relative to a part of a sentence. For longer and more complicated sentences it can be advantageous to cut it in multiple pieces to have a more detailed analysis.

For example: I liked the park but it was raining and the weather was cold would be cut into:

I liked the park but it was raining and the weather was cold

In this case it allows to perform more precise sentiment analysis than assigning a score to the whole sentence.

Subsentence is iterable and will yield instances of Token class.

Attributes / Properties

Name Type Description
tokens list of Token instances List of Token in the subsentence
common properties depends on property Properties allowing access to specific data (pos, token etc.)

Token Class

Token stores data relative to a specific token. Tokens are delimited according to our Tokenizer.

Attributes / Properties

Name Type Description
common properties depends on property Properties allowing access to specific data (pos, token etc.)

Common properties

These properties are accessible at all analysis levels : NLP, Document, Sentence, Subsentence, Token.

All properties have a _flat variant (token_flat) which flatten recursively the return.

Name type Description
str String Returns sentence as string
token String Returns token
lemma String Returns lemma
pos String Returns POS (Part-Of-Speech) tags
dep String Returns dependency relations
morphology String Returns morphological features
language String Returns detected language
meaning List of Tuples Returns meanings as tuples (SUPER, SUB)
emotion Tuple Returns emotion as tuple (Type, score)
sentiment Dictionary Returns sentiment with positive, negative and total values
sentiment_ml Dictionary Returns sentiment of ml_model without further fine tuning
sentiment_target Tuple Returns 'target' of words with strong sentimental meaning
sentence_type String Returns type of sentence
coreference String Returns reference of token if it exists
synthesis Dictionary Returns synthesis object

Sentiment Class

Sentiment provides methods to perform some specific sentiment and emotion analysis. It takes as input an instance of NLP and uses it to retrieve data.

import lettria
from lettria import Sentiment
nlp = lettria.NLP(api_key)
nlp.add_document(['sentence 1', 'sentence 2'])

sentiment = Sentiment(nlp)

Attributes / Properties

Name Type Description
nlp NLP class Instance of NLP class

Methods

Name Description
get_emotion() Returns emotion results at the specified hierarchical level
get_sentiment() Returns sentiment results at the specified hierarchical level
word_sentiment() Returns average sentiment for each word of the whole vocabulary
meaning_sentiment() Returns average sentiment for each meaning
filter_polarity() Filters Sentence or Subsentence of the specified polarity
filter_emotion() Filters Sentence or Subsentence of the specified emotions

get_emotion

get_emotion(level='document')

Returns emotion results at the specified hierarchical level. For example get_emotion(level='document') will concatenate emotion at the document level and return a list of emotions for each Document.

Parameters:

Name Type Description Optional
level string Hierarchical level at which results are concatened.
One of 'global', 'document', 'sentence', 'subsentence'.
True

Return:

Type Description
list of dict List of dictionaries with emotions as keys and dict {'occurences','sum','average'} as values.

get_sentiment

get_sentiment(level='document')

Returns sentiment results at the specified hierarchical level For example get_sentiment(level='document') will concatenate sentiment at the document level and return a list of emotions for each Document.

Parameters:

Name Type Description Optional
level string Hierarchical level at which results are concatened.
One of 'global', 'document', 'sentence', 'subsentence'.
True

Return:

Type Description
list of dict List of dictionaries with polarity as keys and dict {'occurences','sum','average'} as values.

word_sentiment

word_sentiment(granularity = 'sentence', lemma = False, filter_pos = None)

Returns an average sentiment score for each word or lemma in the data. For each sentence or subsentence, the sentiment score is added to each of the words in the phrase. The scores are divided by the number of occurences to get an average.

Parameters:

Name Type Description Optional
granularity string Whether to use sentiment by 'sentence' or 'subsentence' for scoring. True
lemma bool Whether to use lemma or plain words. True
filter_pos list of string POStags to use for filtering. True

Return:

Type Description
dictionary Dictionary with words as keys and sentiment as value

meaning_sentiment

meaning_sentiment(granularity='sentence', filter_meaning=None)

Returns average sentiment score for each meaning For each sentence or subsentence, the sentiment score is added to each of the meaning in the phrase. The scores are divided by the number of occurences to get an average. For example, this can be used with custom meaning to get a sentiment associated with customer service or pricing when analyzing reviews.

Parameters:

Name Type Description Optional
granularity string Whether to use sentiment by 'sentence' or 'subsentence' for scoring. True
filter_meaning list of string Filters results by list of meanings True

Return:

Type Description
dictionary Dictionary with meanings as keys and sentiment as value

filter_polarity

filter_polarity(polarity, granularity='sentence')

Filters Sentence or Subsentence of the specified polarity.

Parameters:

Name Type Description Optional
polarity string Polarity, one of 'neutral', 'positive', 'negative'. False
granularity string Whether to use sentiment by 'sentence' or 'subsentence' for scoring. True

Return:

Type Description
list of instances of Sentence or Subsentence List of instances of objects with the specified polarity.

filter_emotion

filter_emotion(emotions, granularity='sentence')

Filters Sentence of the specified emotions.

Parameters:

Name Type Description Optional
emotions list of string Emotions to filter. False
granularity string Whether to use sentiment by 'sentence' or 'subsentence' for scoring. True

Return:

Type Description
list of instances of Sentence or Subsentence List of instances of objects with the specified emotions.

Client Class

Client used to perform requests to our API.

Attributes / Properties

Name Type Description
key string The API_KEY that will be used by the client.

Methods

METHOD DESCRIPTION
request() Send a request to our API

request

request(text)

Performs a request to lettria API using the API_KEY provided.

Parameters:

Name Type Description Optional
text string Text data to be sent to the API False

Return:

Type Description
list of dictionary Each of these objects represents the informations collected for a sentence.

API

When you make a request to our API, we first split your text into sentences. Each sentence is processed individually, and the results from each analysis is then compiled into one JSON object. This JSON object is a list of Lettria Sentence Object.

Lettria Sentence Object

In this object, each key corresponds to the returned object from a sub-API.

KEY TYPE DESCRIPTION
tokenizer list of string List of tokens
Entities_numeral list of Numeral Entity Object -
NER list of NER Object Lists all the Numeral Entities and Named Entities found in the sentence
NLP list of NLP Object Lemma for each token in the sentence
NLU list of NLU Object Understanding for each token in the sentence
language_used Language used Object Language detection
disturbance list of Disturbance Object List of spell-checking objects for each token in the sentence
parser_dependency list of Dependency Object Dependencie for tokens in the sentence
postagger list of POS Tagger Object List of token - tag tuples
coreference list of Coreference Object List of found coreferences
emotions Emotions Object Emotion analysis of the sentence
sentiment Sentiment Object Sentiment analysis of the sentence
sentence_acts Sentence Acts Object Detection of sentence type
proposition list of Subsentence Object List of subsentences found within the sentence
synthesis list of Synthesis Token Object compiles all the most relevant information for each token

Synthesis

[
  {
    "type": null,
    "lemma": "je",
    "meaning": [
      {
        "sub": "Pronom",
        "super": null
      }
    ],
    "tag": "CLS",
    "value": "S-1",
    "source": "je",
    "nlp": {
      "lemmatizer": {
        "confidence": 0.99,
        "pronom": 1
      },
      "source": "je",
      "tag": "CLS"
    },
    "nlp_items": null,
    "coreference": {
      "category": [
        "human"
      ],
      "category_parent": [
        "PERSON"
      ],
      "id": 0,
      "lemma": "USER",
      "source": "USER"
    }
  },
  {
    "type": null,
    "lemma": "adorer",
    "meaning": [
      {
        "sub": "sentiment_love",
        "super": "SENTIMENT"
      }
    ],
    "tag": "V",
    "value": null,
    "source": "adore",
    "nlp": {
      "lemmatizer": [
        {
          "confidence": 0.99,
          "conjugate": [
            {
              "mode": "imperative",
              "pronom": 2,
              "temps": "present"
            },
            {
              "mode": "indicative",
              "pronom": 3,
              "temps": "present"
            },
            {
              "mode": "participe",
              "pronom": -1,
              "temps": "past"
            },
            {
              "mode": "subjonctive",
              "pronom": 3,
              "temps": "present"
            },
            {
              "mode": "indicative",
              "pronom": 1,
              "temps": "present"
            },
            {
              "mode": "subjonctive",
              "pronom": 1,
              "temps": "present"
            }
          ],
          "infinit": "adorer"
        }
      ],
      "source": "adore",
      "tag": "V"
    },
    "nlp_items": null,
    "coreference": null
  },
  {
    "type": null,
    "lemma": "!",
    "meaning": [],
    "tag": "PUNCT",
    "value": null,
    "source": "!",
    "nlp": {
      "lemmatizer": {
        "confidence": 0.79
      },
      "source": "!",
      "tag": "PUNCT"
    },
    "nlp_items": null,
    "coreference": null
  }
]
[
  {
    "type": null,
    "lemma": "je",
    "meaning": [
      {
        "sub": "Pronom",
        "super": null
      }
    ],
    "tag": "CLS",
    "value": "S-1",
    "source": "je",
    "nlp": {
      "lemmatizer": {
        "confidence": 0.99,
        "pronom": 1
      },
      "source": "je",
      "tag": "CLS"
    },
    "nlp_items": null,
    "coreference": {
      "category": [
        "human"
      ],
      "category_parent": [
        "PERSON"
      ],
      "id": 0,
      "lemma": "USER",
      "source": "USER"
    }
  },
  {
    "type": null,
    "lemma": "adorer",
    "meaning": [
      {
        "sub": "sentiment_love",
        "super": "SENTIMENT"
      }
    ],
    "tag": "V",
    "value": null,
    "source": "adore",
    "nlp": {
      "lemmatizer": [
        {
          "confidence": 0.99,
          "conjugate": [
            {
              "mode": "imperative",
              "pronom": 2,
              "temps": "present"
            },
            {
              "mode": "indicative",
              "pronom": 3,
              "temps": "present"
            },
            {
              "mode": "participe",
              "pronom": -1,
              "temps": "past"
            },
            {
              "mode": "subjonctive",
              "pronom": 3,
              "temps": "present"
            },
            {
              "mode": "indicative",
              "pronom": 1,
              "temps": "present"
            },
            {
              "mode": "subjonctive",
              "pronom": 1,
              "temps": "present"
            }
          ],
          "infinit": "adorer"
        }
      ],
      "source": "adore",
      "tag": "V"
    },
    "nlp_items": null,
    "coreference": null
  },
  {
    "type": null,
    "lemma": "!",
    "meaning": [],
    "tag": "PUNCT",
    "value": null,
    "source": "!",
    "nlp": {
      "lemmatizer": {
        "confidence": 0.79
      },
      "source": "!",
      "tag": "PUNCT"
    },
    "nlp_items": null,
    "coreference": null
  }
]

Compiles all the most relevant information for each token.

Go back to the Sentence Object.

Synthesis Token Object

Links in this section will redirect you to their origin in the given sub-api.

KEY TYPE DESCRIPTION CONSTRAINTS
type string Describes the type of entity found For proper nouns, can either be LOCATION or PERSON. For other entities, see Entity types
lemma string lemma of the word -
meaning list of Category Objects Known meanings for the item Can be empty.
tag string see Tags -
value Value Object Value for numeral entities Can be Null
source string original string input related to the token -
nlp list of NLP Objects if NULL refer to nlp_items Can be Null
nlp_items list of NLP Objects This is where you can find individual NLP informations when multiple tokens get merged to form one entity (example : "12" + "kg") Can be Null
coreference Coreference Object - -

Emoticons

{
    "confidence": "0.89",
    "emoticon": {
        "Thappy": 0,
        "angel": 0,
        "cry": 0,
        "devil": 0,
        "embarrassed": 0,
        "happy": 0,
        "hesitant": 0,
        "horror": 0,
        "indecision": 0,
        "kiss": 0,
        "lol": 0,
        "love": 0,
        "muted": 0,
        "notlove": 0,
        "playful": 0,
        "sad": 0,
        "surprise": 0,
        "very_happy": 0,
        "very_sad": 0,
        "wink": 0
    }
}
{
    "confidence": "0.89",
    "emoticon": {
        "Thappy": 0,
        "angel": 0,
        "cry": 0,
        "devil": 0,
        "embarrassed": 0,
        "happy": 0,
        "hesitant": 0,
        "horror": 0,
        "indecision": 0,
        "kiss": 0,
        "lol": 0,
        "love": 0,
        "muted": 0,
        "notlove": 0,
        "playful": 0,
        "sad": 0,
        "surprise": 0,
        "very_happy": 0,
        "very_sad": 0,
        "wink": 0
    }
}

List all emoticons found.

KEY TYPE DESCRIPTION CONSTRAINTS
confidence float Confidence in value matching
emoticon EmoticonObject boolean values for matched emoticons

EmoticonObject

KEY TYPE DESCRIPTION CONSTRAINTS
Thappy int - 0 or 1
angel int - 0 or 1
cry int - 0 or 1
devil int - 0 or 1
embarrassed int - 0 or 1
happy int - 0 or 1
hesitant int - 0 or 1
horror int - 0 or 1
indecision int - 0 or 1
kiss int - 0 or 1
lol int - 0 or 1
love int - 0 or 1
muted int - 0 or 1
notlove int - 0 or 1
playful int - 0 or 1
sad int - 0 or 1
surprise int - 0 or 1
very_happy int - 0 or 1
very_sad int - 0 or 1
wink int - 0 or 1

Language Used

"sentence_level":{
    "label":"fr",
    "accuracy":0.8050500154495239
    },
    "word_level":
    {
    "i":1,
    "source":"je",
    "language":[
        {
        "label":"sr",
        "accuracy":0.8350609540939331
        },
        {
        "label":"fr",
        "accuracy":0.15938909351825714
        },
        {
        "label":"sl",
        "accuracy":0.003785850713029504
        }
    ]
    },
    {
    "i":2,
    "source":"suis",
    "language":[
        {
        "label":"fr",
        "accuracy":0.9970543384552002
        },
        {
        "label":"en",
        "accuracy":0.002935485215857625
        },
        {
        "label":"la"
        "accuracy":0.00004386376895126887
        }
    ]
    },
    {
    "i":3,
    "source":"Lettria",
    "language":[
        {
        "label":"it",
        "accuracy":0.9687148332595825
        },
        {
        "label":"de",
        "accuracy":0.012400689534842968
        },
        {
        "label":"es",
        "accuracy":0.003765000030398369
        }
    ]
    }
    ],
    "predict":"fr"
}
"sentence_level":{
    "label":"fr",
    "accuracy":0.8050500154495239
    },
    "word_level":
    {
    "i":1,
    "source":"je",
    "language":[
        {
        "label":"sr",
        "accuracy":0.8350609540939331
        },
        {
        "label":"fr",
        "accuracy":0.15938909351825714
        },
        {
        "label":"sl",
        "accuracy":0.003785850713029504
        }
    ]
    },
    {
    "i":2,
    "source":"suis",
    "language":[
        {
        "label":"fr",
        "accuracy":0.9970543384552002
        },
        {
        "label":"en",
        "accuracy":0.002935485215857625
        },
        {
        "label":"la"
        "accuracy":0.00004386376895126887
        }
    ]
    },
    {
    "i":3,
    "source":"Lettria",
    "language":[
        {
        "label":"it",
        "accuracy":0.9687148332595825
        },
        {
        "label":"de",
        "accuracy":0.012400689534842968
        },
        {
        "label":"es",
        "accuracy":0.003765000030398369
        }
    ]
    }
    ],
    "predict":"fr"
}

Go back to the Sentence Object.

Language used Object

Language code follows ISO 639-1.

KEY TYPE DESCRIPTION CONSTRAINTS
predict string cast fr because Lettria exits in French actually -
sentence level Language Object Predict language of sentence -
word level Language Object Predict language per word -

Language Object

probabilities for 140 languages

KEY TYPE DESCRIPTION CONSTRAINTS
da float Danish -
de float German -
en float English -
es float Spanish -
fi float Finnish -
fr float French -
hu float Hungarian -
it float Italian -
kk float Kazakh -
nl float Dutch -
no float Norwegian -
pt float Portuguese -
ru float Russian -
sv float Swedish -
tr float Turkish -
... float ...

POS Tagger

[
    [
        "vous",
        "CLS"
    ],
    [
        "avez",
        "V"
    ],
    [
        "acces",
        "N"
    ],
    [
        "a",
        "P"
    ],
    [
        "la",
        "D"
    ],
    [
        "meilleure",
        "JJ"
    ],
    [
        "comprehension",
        "N"
    ],
    [
        "du",
        "P"
    ],
    [
        "langage",
        "N"
    ]
]
[
    [
        "vous",
        "CLS"
    ],
    [
        "avez",
        "V"
    ],
    [
        "acces",
        "N"
    ],
    [
        "a",
        "P"
    ],
    [
        "la",
        "D"
    ],
    [
        "meilleure",
        "JJ"
    ],
    [
        "comprehension",
        "N"
    ],
    [
        "du",
        "P"
    ],
    [
        "langage",
        "N"
    ]
]

Go back to the Sentence Object.

POS Tagger Object

INDEX TYPE DESCRIPTION CONSTRAINTS
0 string Word token -
1 string See list of possible tags -

disturbance

[
  {
  "original":"pierre",
  "predict":"pierre",
  "to_correct":0
  },
  {
  "original":"aime",
  "predict":"aime",
  "to_correct":0
  },
  {
  "original":"les",
  "predict":"les",
  "to_correct":0
  },
  {
  "original":"banans",
  "predict":"banane",
  "probabilities":{
      "banals":2,
      "banane":0,
      "bananes":1,
      "banats":3,
      "banians":3,
      "bannans":3,
      "bannas":3,
      "bavans":3,
      "nanans":3
    },
  "to_correct":0
  }
]
[
  {
  "original":"pierre",
  "predict":"pierre",
  "to_correct":0
  },
  {
  "original":"aime",
  "predict":"aime",
  "to_correct":0
  },
  {
  "original":"les",
  "predict":"les",
  "to_correct":0
  },
  {
  "original":"banans",
  "predict":"banane",
  "probabilities":{
      "banals":2,
      "banane":0,
      "bananes":1,
      "banats":3,
      "banians":3,
      "bannans":3,
      "bannas":3,
      "bavans":3,
      "nanans":3
    },
  "to_correct":0
  }
]

Go back to the Sentence Object.

Disturbance Object

Spell-checking object. Each token is associated with an object and is checked against our dictionary. If the token does not exist, a list of candidates will be suggested along with the most likely replacement. Gender and plural are not taken into account as the lemma will be the same regardless.

KEY TYPE DESCRIPTION CONSTRAINTS
original string token as found in the sentence -
predict string predicted token after spell-checking, same as original for valid words -
probabilities dictionary candidates for correction with correspond rank (0 being the most likely candidate) Key only exists if word should be corrected
to_correct int 1 if token should be corrected but no replacement has been found 0 or 1

NLP

[
    {
        "lemmatizer": {
            "gender": {
                "female": false,
                "plural": false
            },
            "mode": "define",
            "possessing": -1
        },
        "source": "le",
        "tag": "D"
    },
    {
        "lemmatizer": {
            "confidence": "0.99",
            "gender": {
                "female": false,
                "plural": false
            },
            "lemma": "chemin"
        },
        "source": "chemin",
        "tag": "N"
    },
    {
        "lemmatizer": [
            {
                "confidence": "0.99",
                "conjugate": [
                    {
                        "mode": "indicative",
                        "pronom": 3,
                        "temps": "present"
                    }
                ],
                "infinit": "etre"
            }
        ],
        "source": "est",
        "tag": "V"
    },
    {
        "lemmatizer": {
            "confidence": "0.99",
            "gender": {
                "female": false,
                "plural": false
            },
            "lemma": "long"
        },
        "source": "long",
        "tag": "JJ"
    },
    {
        "source": ".",
        "tag": "PUNCT"
    }
]
[
    {
        "lemmatizer": {
            "gender": {
                "female": false,
                "plural": false
            },
            "mode": "define",
            "possessing": -1
        },
        "source": "le",
        "tag": "D"
    },
    {
        "lemmatizer": {
            "confidence": "0.99",
            "gender": {
                "female": false,
                "plural": false
            },
            "lemma": "chemin"
        },
        "source": "chemin",
        "tag": "N"
    },
    {
        "lemmatizer": [
            {
                "confidence": "0.99",
                "conjugate": [
                    {
                        "mode": "indicative",
                        "pronom": 3,
                        "temps": "present"
                    }
                ],
                "infinit": "etre"
            }
        ],
        "source": "est",
        "tag": "V"
    },
    {
        "lemmatizer": {
            "confidence": "0.99",
            "gender": {
                "female": false,
                "plural": false
            },
            "lemma": "long"
        },
        "source": "long",
        "tag": "JJ"
    },
    {
        "source": ".",
        "tag": "PUNCT"
    }
]

Go back to the Sentence Object.

NLP Object

KEY TYPE DESCRIPTION CONSTRAINTS
source string Words composing the token -
tag string see Tags -
lemmatizer Lemmatizer Object Object with information regarding lemma of token -

Lemmatizer Object

The content of the lemmatizer object is different for each tag. The table bellow references all the keys that are available, and lists the tags that will return them (see POS Tagger and list of tags).

KEY TYPE DESCRIPTION CONSTRAINTS TAGS
conjugate list of Conjugate Objects List possible conjugations see Conjugations V
confidence float level of confidence in the results (higher is better) 0 <= confidence <= 1 (all)
gender Gender Object describes the gender and plurality - VP, JJ, N, D, PD
lemma string lemmatized version of the source - C, CC, CLO, CLS, D, JJ, N, NP, PUNCT, P, PD, PROREL, RB, RB_WH, SYM, UH
infinit list of string list of possible verb infinitives - V, VP
number float value - CD
mode string - - D, PD
possessing int see Possessive determiners - D, PD
pronom int see Pronouns - CLS
designation list of string see Categories - CLO
category string see Adverb Categories - RB
source string - - RB, P
sens list of Preposition sens object - - P

Conjugate Object

Decribes the possible conjugations for a given verb.

KEY TYPE DESCRIPTION CONSTRAINTS
mode string - -
pronom int see Pronouns -
temps string - -

Gender Object

Gives information about the gender and plurality of a word.

KEY TYPE DESCRIPTION CONSTRAINTS
female bool - true or false
plural bool - true or false

Preposition sens Object

Describes prepositions. See Preposition categories.

KEY TYPE DESCRIPTION CONSTRAINTS
sens string see Preposition sens
category string see Preposition categories
next string see Preposition next

NLU

[
    {
        "compose":[

        ],
        "index":0,
        "len":1,
        "meaning":[
            "Pronom"
        ],
        "source":"je",
        "value":"S-1"
    },
    {
        "compose":[

        ],
        "index":1,
        "infinit":[
            "manger"
        ],
        "len":1,
        "meaning":[
            "action_feed",
            "action_eat"
        ],
        "source":"mange",
        "value":None,
        "verb_meaning":{
            "manger":[
                "action_feed",
                "action_eat"
            ]
        }
    },
    {
        "compose":[

        ],
        "index":2,
        "len":1,
        "meaning":[
            "Number"
        ],
        "source":"une",
        "value":1
    },
    {
        "compose":[

        ],
        "index":3,
        "len":1,
        "meaning":[
            "color",
            "firstname",
            "fruit"
        ],
        "source":"pomme",
        "value":None
    }
]
[
    {
        "compose":[

        ],
        "index":0,
        "len":1,
        "meaning":[
            "Pronom"
        ],
        "source":"je",
        "value":"S-1"
    },
    {
        "compose":[

        ],
        "index":1,
        "infinit":[
            "manger"
        ],
        "len":1,
        "meaning":[
            "action_feed",
            "action_eat"
        ],
        "source":"mange",
        "value":None,
        "verb_meaning":{
            "manger":[
                "action_feed",
                "action_eat"
            ]
        }
    },
    {
        "compose":[

        ],
        "index":2,
        "len":1,
        "meaning":[
            "Number"
        ],
        "source":"une",
        "value":1
    },
    {
        "compose":[

        ],
        "index":3,
        "len":1,
        "meaning":[
            "color",
            "firstname",
            "fruit"
        ],
        "source":"pomme",
        "value":None
    }
]

Understanding for each token in the sentence.

Go back to the Sentence Object.

NLU Object

KEY TYPE DESCRIPTION CONSTRAINTS
index int Index in the initial tokenized sentence index >= 0
len int Number of tokens that have been merged (1 if no merge) len >= 1
meaning list of Category Objects Known meanings for the item Can be empty.
source string - if len is greater than one, will be the merged sources of original items
value dict Depends on tag. Most values are in the 'scalar' key of this dict Can be None

Entities numeral

[
    {
        "entity": {
            "centimeter": 200.0,
            "confidence": 0.99,
            "feet": 6.561679790026246,
            "inches": 78.74015748031496,
            "kilometer": 0.002,
            "meter": 2.0,
            "miles": 0.001242742,
            "scalar": 2.0,
            "unit": "m",
            "yard": 2.1872
        },
        "source": "2m",
        "tag": "distance"
    }
]
[
    {
        "entity": {
            "centimeter": 200.0,
            "confidence": 0.99,
            "feet": 6.561679790026246,
            "inches": 78.74015748031496,
            "kilometer": 0.002,
            "meter": 2.0,
            "miles": 0.001242742,
            "scalar": 2.0,
            "unit": "m",
            "yard": 2.1872
        },
        "source": "2m",
        "tag": "distance"
    }
]

Go back to the Sentence Object.

Numeral Entity Object

KEY TYPE DESCRIPTION CONSTRAINTS
entity Entity Object - -
source string - -
tag string see Entity types -

NER

[
  {
    "source": "Paris",
    "type": "LOCATION",
    "value": null
  },
  {
    "source": "12 mai",
    "type": "date",
    "value": {
      "ISO": "2019-05-12",
      "chronology": "future",
      "chronology_day": 58,
      "confidence": 0.99,
      "formatted": "Sunday 12 May 2019 00:00:00",
      "timestamp": 1557612000
    }
  }
]
[
  {
    "source": "Paris",
    "type": "LOCATION",
    "value": null
  },
  {
    "source": "12 mai",
    "type": "date",
    "value": {
      "ISO": "2019-05-12",
      "chronology": "future",
      "chronology_day": 58,
      "confidence": 0.99,
      "formatted": "Sunday 12 May 2019 00:00:00",
      "timestamp": 1557612000
    }
  }
]

The NER sub-api lists all the Numeral Entities and Named Entities found in the sentence.

Go back to the Sentence Object.

NER Object

KEY TYPE DESCRIPTION CONSTRAINTS
source string - -
type string Describes the type of entity found For proper nouns, can either be LOCATION or PERSON. For other entities, see Entity types
value Value Object - -

Value Object

A value object can either be a numeric value for some adjectives, an entity value for entities, or a 'null' value for names.

Parser dependency

[
  {
    "dep": "nsubj",
    "index": 0,
    "lemma": "je",
    "len": 1,
    "meaning": [
      {
        "sub": "Pronom",
        "super": null
      }
    ],
    "ref": 1,
    "source": "je",
    "tag": "CLS",
    "value": "S-1"
  },
  {
    "dep": "root",
    "index": 1,
    "lemma": "promener",
    "len": 1,
    "meaning": [
      {
        "sub": "action_walk",
        "super": "ACTION"
      },
      {
        "sub": "action_move",
        "super": "ACTION"
      }
    ],
    "ref": -1,
    "source": "promene",
    "tag": "V",
    "value": null
  },
  {
    "dep": "det",
    "index": 2,
    "lemma": "mon",
    "len": 1,
    "meaning": [],
    "ref": 3,
    "source": "mon",
    "tag": "D",
    "value": null
  },
  {
    "dep": "obj",
    "index": 3,
    "lemma": "chien",
    "len": 1,
    "meaning": [
      {
        "sub": "dog",
        "super": "ANIMAL"
      }
    ],
    "ref": 1,
    "source": "chien",
    "tag": "N",
    "value": null
  }
]
[
  {
    "dep": "nsubj",
    "index": 0,
    "lemma": "je",
    "len": 1,
    "meaning": [
      {
        "sub": "Pronom",
        "super": null
      }
    ],
    "ref": 1,
    "source": "je",
    "tag": "CLS",
    "value": "S-1"
  },
  {
    "dep": "root",
    "index": 1,
    "lemma": "promener",
    "len": 1,
    "meaning": [
      {
        "sub": "action_walk",
        "super": "ACTION"
      },
      {
        "sub": "action_move",
        "super": "ACTION"
      }
    ],
    "ref": -1,
    "source": "promene",
    "tag": "V",
    "value": null
  },
  {
    "dep": "det",
    "index": 2,
    "lemma": "mon",
    "len": 1,
    "meaning": [],
    "ref": 3,
    "source": "mon",
    "tag": "D",
    "value": null
  },
  {
    "dep": "obj",
    "index": 3,
    "lemma": "chien",
    "len": 1,
    "meaning": [
      {
        "sub": "dog",
        "super": "ANIMAL"
      }
    ],
    "ref": 1,
    "source": "chien",
    "tag": "N",
    "value": null
  }
]

Go back to the Sentence Object.

Dependency Object

Dependence objects combine the results from the dependency parser with the understanding from the NLU api.

KEY TYPE DESCRIPTION CONSTRAINTS
dep string see list of dependency tags -
index int base index of the token, links the APIs together index >= 0
lemma string - -
meaning list of Category Objects - -
ref int index of the parent dependence -1 for root, else >= 0
tag string see Tags -
value Value Object - -
source string source -

Coreference

[
    {
        "index": 0, 
        "precision": 0.3, 
        "reference": 
        {
            "category": 
            [
                "human"
            ], 
            "category_parent": 
            [
                "PERSON"
            ], 
            "id": 0, 
            "lemma": "USER", 
            "source": "USER"
        }, 
        "source": "je"
    }, 
    {
        "index": 1, 
        "precision": 0.6, 
        "reference": 
        {
            "category": 
            [
                "dog"
            ], 
            "category_parent": 
            [
                "ANIMAL"
            ], 
            "id": 179, 
            "lemma": "chien", 
            "source": "chien"
        }, 
    "source": "le"
    }
]
[
    {
        "index": 0, 
        "precision": 0.3, 
        "reference": 
        {
            "category": 
            [
                "human"
            ], 
            "category_parent": 
            [
                "PERSON"
            ], 
            "id": 0, 
            "lemma": "USER", 
            "source": "USER"
        }, 
        "source": "je"
    }, 
    {
        "index": 1, 
        "precision": 0.6, 
        "reference": 
        {
            "category": 
            [
                "dog"
            ], 
            "category_parent": 
            [
                "ANIMAL"
            ], 
            "id": 179, 
            "lemma": "chien", 
            "source": "chien"
        }, 
    "source": "le"
    }
]

Go back to the Sentence Object.

Coreference Object

KEY TYPE DESCRIPTION CONSTRAINTS
source string source word that makes the coreference query -
index int index of the source word index >= 0
precision float precision indices based on how the algorithm found the coreference. Higher is better 0 <= precision <= 1
reference Reference Object describes the best match for the coreference query

Reference Object

KEY TYPE DESCRIPTION CONSTRAINTS
source string source word of the reference object -
lemma string lemma of the reference -
id int database id of the reference id > 0. Unique for each reference object created
category list of string reference's categories -
category_parent list of string parent categories of reference's categories -

Sentence Acts

{
  "predict": "question_open",
  "probabilities": {
    "assert": 0.24,
    "command": 0,
    "exclam": 0.06,
    "question_open": 0.7,
    "question_yn": 0
  }
}
{
  "predict": "question_open",
  "probabilities": {
    "assert": 0.24,
    "command": 0,
    "exclam": 0.06,
    "question_open": 0.7,
    "question_yn": 0
  }
}

Go back to the Sentence Object.

Sentence_acts Object

Detail of the sentence_acts list:

KEY TYPE DESCRIPTION CONSTRAINTS
predict string Type chosen by the algorithm. -
probabilities Sentence_acts detail Object Detail of the probabilities of each types. -

Sentence_acts detail Object

KEY TYPE DESCRIPTION EXAMPLE
assert float Probability that the sentence is an assertion. "Je suis un développeur."
command float Probability that the sentence is a command. "Donne moi la réponse."
exclam float Probability that the sentence is ane exclamation. "Cette API est géniale !"
question_open float Probability that the sentence is an open-ended question. "Quelle est la meilleure solution de TALN en français ?"
question_yn float Probability that the sentence is a close-ended question. "Est-ce que vous avez une question ?"

emotions

{
    "elements": [
        {
            "source": {
                "index": 1,
                "lemma": "aimer",
                "source": "aime"
            },
            "subject": {
                "index": 0,
                "lemma": "il",
                "source": "elle"
            },
            "target": {
                "index": 3,
                "lemma": "chien",
                "source": "chiens"
            },
            "type": "happiness",
            "value": 0.46
        }
    ],
    "values": {
        "anger": 0,
        "disgust": 0,
        "fear": 0,
        "happiness": 0.17,
        "sadness": 0,
        "surprise": 0
    },
    "subsentences": {
        "sentence": "elle aime les chiens",
        "start_id": 0,
        "end_id": 3,
        "elements": [
            {
                "source": {
                    "index": 1,
                    "lemma": "aimer",
                    "source": "aime"
                },
                "subject": {
                    "index": 0,
                    "lemma": "il",
                    "source": "elle"
                },
                "target": {
                    "index": 3,
                    "lemma": "chien",
                    "source": "chiens"
                },
                "type": "happiness",
                "value": 0.46
            }
        ],
        "values": {
                "negative": 0,
                "positive": 0.27,
                "total": 0.27
        }
    }
}
{
    "elements": [
        {
            "source": {
                "index": 1,
                "lemma": "aimer",
                "source": "aime"
            },
            "subject": {
                "index": 0,
                "lemma": "il",
                "source": "elle"
            },
            "target": {
                "index": 3,
                "lemma": "chien",
                "source": "chiens"
            },
            "type": "happiness",
            "value": 0.46
        }
    ],
    "values": {
        "anger": 0,
        "disgust": 0,
        "fear": 0,
        "happiness": 0.17,
        "sadness": 0,
        "surprise": 0
    },
    "subsentences": {
        "sentence": "elle aime les chiens",
        "start_id": 0,
        "end_id": 3,
        "elements": [
            {
                "source": {
                    "index": 1,
                    "lemma": "aimer",
                    "source": "aime"
                },
                "subject": {
                    "index": 0,
                    "lemma": "il",
                    "source": "elle"
                },
                "target": {
                    "index": 3,
                    "lemma": "chien",
                    "source": "chiens"
                },
                "type": "happiness",
                "value": 0.46
            }
        ],
        "values": {
                "negative": 0,
                "positive": 0.27,
                "total": 0.27
        }
    }
}

Go back to the Sentence Object.

Emotions Object

KEY TYPE DESCRIPTION CONSTRAINTS
subsentences list of Subsentences Emotions Element Object Source of all emotions elements divided by subsentences -
elements list of Emotions Element Object Specific source for all emotion elements in the sentence -
values Emotions Values Object normalized total values for emotion -

Emotions values are available at the following levels of granularity: sentence, subsentence and element.

Emotions Subsentences Object

KEY TYPE DESCRIPTION CONSTRAINTS
sentence string Source of all emotions elements divided by subsentences -
start_id int Id of the first token of the subsentence -
end_id int Id of the last token of the subsentence -
elements list of Emotions Element Objets Specific source for all emotion elements in the subsentence -
values Emotions Values Object normalized values for emotion of subsentence -

Emotions Element Object

KEY TYPE DESCRIPTION CONSTRAINTS
source index int Index of the source word for this element
- lemma string source's lemma
- lemma string source's source
subject index int Index of the subject for this element
- lemma string subject's lemma
- source string subject's source
target index int Index of the target for this element
- lemma string target's lemma
- source string target's source
type - string Type of emotion
value - float Indice of the emotion

Subject is the word which represents the subject of the action

"[Je] aime [les] [pommes]"

Source is the word which conveys the emotion

"[Je] aime les pommes"

Target is the word which represents the target of the emotion

"[Je] aime les pommes" "Pierre est content"

Emotions Values Object

KEY TYPE DESCRIPTION CONSTRAINTS
happiness float normalized total 0 <= happiness < 1
sadness float normalized total 0 <= sadness < 1
anger float normalized total -1 < anger < 1
surprise float normalized total -1 < surprise < 1
disgust float normalized total -1 < disgust < 1
fear float normalized total -1 < fear < 1

Values are calculated by using emotion elements objects. Values are normalized to stay in the the [-1 : 1] interval between element, subsentence and sentence level therefore comparisons should be made made with elements of the same depth.

sentiment

{
    "elements": [
        {
            "source": {
                "index": 1,
                "lemma": "aimer",
                "source": "aime"
            },
            "subject": {
                "index": 0,
                "lemma": "il",
                "source": "elle"
            },
            "target": {
                "index": 3,
                "lemma": "chien",
                "source": "chiens"
            },
            "value": 0.46
        }
    ],
    "values": {
        "negative": 0,
        "positive": 0.17,
        "total": 0.17
    },
    "subsentences": {
        "sentence": "elle aime les chiens",
        "start_id": 0,
        "end_id": 3,
        "elements": [
            {
                "source": {
                    "index": 1,
                    "lemma": "aimer",
                    "source": "aime"
                },
                "subject": {
                    "index": 0,
                    "lemma": "il",
                    "source": "elle"
                },
                "target": {
                    "index": 3,
                    "lemma": "chien",
                    "source": "chiens"
                },
                "value": 0.27
            }
        ],
        "values": {
                "negative": 0,
                "positive": 0.17,
                "total": 0.17
        }
    }
}
{
    "elements": [
        {
            "source": {
                "index": 1,
                "lemma": "aimer",
                "source": "aime"
            },
            "subject": {
                "index": 0,
                "lemma": "il",
                "source": "elle"
            },
            "target": {
                "index": 3,
                "lemma": "chien",
                "source": "chiens"
            },
            "value": 0.46
        }
    ],
    "values": {
        "negative": 0,
        "positive": 0.17,
        "total": 0.17
    },
    "subsentences": {
        "sentence": "elle aime les chiens",
        "start_id": 0,
        "end_id": 3,
        "elements": [
            {
                "source": {
                    "index": 1,
                    "lemma": "aimer",
                    "source": "aime"
                },
                "subject": {
                    "index": 0,
                    "lemma": "il",
                    "source": "elle"
                },
                "target": {
                    "index": 3,
                    "lemma": "chien",
                    "source": "chiens"
                },
                "value": 0.27
            }
        ],
        "values": {
                "negative": 0,
                "positive": 0.17,
                "total": 0.17
        }
    }
}

Go back to the Sentence Object.

Sentiment Object

KEY TYPE DESCRIPTION CONSTRAINTS
subsentences list of Subsentences Sentiment Element Object Source of all sentiments elements divided by subsentences -
elements list of Sentiment Element Object Specific source for all sentiment elements in the sentence -
values Sentiment Values Object normalized total values for sentiment -

Sentiment values are available at the following levels of granularity: sentence, subsentence and element.

Subsentences Sentiment Object

KEY TYPE DESCRIPTION CONSTRAINTS
sentence string Source of all sentiments elements divided by subsentences -
start_id int Id of the first token of the subsentence -
end_id int Id of the last token of the subsentence -
elements list of Sentiment Element Objets Specific source for all sentiment elements in the subsentence -
values Sentiment Values Object normalized values for sentiment of subsentence -

Sentiment Element Object

KEY SUBKEY TYPE DESCRIPTION CONSTRAINTS
source index int Index of the source word for this element -
- lemma string source's lemma -
- lemma string source's source -
subject index int Index of the subject for this element -
- lemma string subject's lemma -
- source string subject's source -
target index int Index of the target for this element -
- lemma string target's lemma -
- source string target's source -
value - float Indice of the sentiment -1 < value < 1

Subject is the word which represents the subject of the action

"[Je] aime [les] [pommes]"

Source is the word which conveys the sentiment

"[Je] aime les pommes"

Target is the word which represents the target of the sentiment

"[Je] aime les pommes" "Pierre est content"

Sentiment Values Object

KEY TYPE DESCRIPTION CONSTRAINTS
positive float normalized addition of all positive sentiment values in the sentence 0 <= positive < 1
negative float normalized addition of all negative sentiment values in the sentence -1 < negative <= 0
total float positive + negative -1 < total < 1

Values are calculated either by using sentiment elements objects if available, or by a prediction model at the subsentence level. Values are normalized to stay in the the [-1 : 1] interval between element, subsentence and sentence level therefore comparisons should be made made with elements of the same depth.

proposition

[
    {
        "start_id":0,
        "end_id":3
    },
    {
        "start_id":4,
        "end_id":9
    }
]
[
    {
        "start_id":0,
        "end_id":3
    },
    {
        "start_id":4,
        "end_id":9
    }
]

Subsentence Object

KEY TYPE DESCRIPTION CONSTRAINTS
start_id int Id of the first token of the subsentence -
end_id int Id of the last token of the subsentence -

GLOSSARY

Tags

List of possible word tags. Used in POS Tagger, Parser Dependency.

VALUE DESCRIPTION EXAMPLES
C conjunction
CC co-ordinating conjunction
CD number
CLO pronoun object
CLS pronoun
D determiner
JJ adjective
N common noun
NP proper noun
PUNCT punctuation
P preposition
PD pronom define
PROREL pronom relative
RB adverb
RB_WH adverb question
SYM symbols
UH interjection
V verb
VINF infinitive verb
VP verb participe past

Dependency Tags

We use the universal dependencies for our dependency parser.

Possessive determiners

VALUE EXAMPLES
1 mon
2 ton
3 son
4 nos
5 vos
6 leur

Pronouns

VALUE EXAMPLES
1 je
2 tu
3 il, elle, on
4 nous
5 vous
6 ils, elles

Conjugations

MODE TENSES
subjonctive present, past
indicative future, past, present
imperative present
participe past, present
conditional present
infinitive infinitive

Entities

These are the entities we can parse.

Entity Types

Acceleration

{
    "ft/s²": 3.0378147176047437e-09,
    "km/h²": 1.2e-05,
    "m/s²": 9.25925925925926e-10,
    "scalar": 12.0,
    "unit": "mm",
    "unit_2": "h",
    "confidence": 0.99
}
{
    "ft/s²": 3.0378147176047437e-09,
    "km/h²": 1.2e-05,
    "m/s²": 9.25925925925926e-10,
    "scalar": 12.0,
    "unit": "mm",
    "unit_2": "h",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
ft/s² float acceleration expressed in feet by second
km/h² float acceleration expressed in kilometers by hour
m/s² float acceleration expressed in feet by second
scalar float source value
unit string source unit of distance
unit-2 string source unit of time
confidence float confidence in value matching

Bandwidth

{
    "kbps": 3000.0,
    "Mbps": 3.0,
    "Gbps": 0.003,
    "scalar": 3000.0,
    "unit": "kbps",
    "confidence": 0.99
}
{
    "kbps": 3000.0,
    "Mbps": 3.0,
    "Gbps": 0.003,
    "scalar": 3000.0,
    "unit": "kbps",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
kbps float bandwidth expressed in kilobit by second
Mbps float bandwidth expressed in megabit by second
Gbps float bandwidth expressed in gigabit by second
scalar float source value
unit string source unit of bandwidth
confidence float confidence in value matching

Data Storage

{
    "kbit": 7000.0,
    "Gbit": 0.007,
    "Mo": 0.875,
    "Go": 0.000875,
    "To": 8.75e-07,
    "scalar": 7.0,
    "unit": "Mbit",
    "confidence": 0.99
}
{
    "kbit": 7000.0,
    "Gbit": 0.007,
    "Mo": 0.875,
    "Go": 0.000875,
    "To": 8.75e-07,
    "scalar": 7.0,
    "unit": "Mbit",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
kbit float data storage expressed in kilobit
Gbit float data storage expressed in megabit
Mo float data storage expressed in megaoctet
Go float data storage expressed in gigaoctet
To float data storage expressed in teraoctet
scalar float source value
unit string source unit of data storage
confidence float confidence in value matching

Date

{
    "ISO": "2017-11-12",
    "formatted": "Sunday 12 November 2017",
    "chronology": "past",
    "chronology_day": 39,
    "confidence": 0.99
}
{
    "ISO": "2017-11-12",
    "formatted": "Sunday 12 November 2017",
    "chronology": "past",
    "chronology_day": 39,
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
ISO string ISO 8601 format aaaa-mm-dd
formatted string the date written in english [weekday name] [Day of the month as a decimal number [01,31]] [month name] [year]
chronology string indicates the chronological relationship between the timestamp of the message and the date ['future', 'past', 'present']
chronology_day int number of days between the date and the timestamp of the message
confidence float confidence for this entity

Debit

{
    "cubic_meter/s": 0.043,
    "cubic_meter/h": 154.79999999999998,
    "mL/s": 43000.0,
    "L/h": 154800.0,
    "L/s": 43.0
    "scalar": 43.0,
    "unit": "l",
    "unit_2": "s",
    "confidence": 0.99
}
{
    "cubic_meter/s": 0.043,
    "cubic_meter/h": 154.79999999999998,
    "mL/s": 43000.0,
    "L/h": 154800.0,
    "L/s": 43.0
    "scalar": 43.0,
    "unit": "l",
    "unit_2": "s",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
cubic_meter/s float debit expressed in cubic meter by second
cubic_meter/h float debit expressed in cubic meter by hour
mL/s float debit expressed in milliliter by second
L/h float debit expressed in liter by hour
L/s float debit expressed in liter by second
scalar float source value
unit string source unit
confidence float confidence in value matching

Distance

{
    "kilometer": 0.0555,
    "inches": 2185.0393700787404,
    "feet": 182.08661417322833,
    "centimeter": 5550.0,
    "meter": 55.5,
    "miles": 0.034486090500000004,
    "yard": 60.694799999999994,
    "scalar": 55.5,
    "unit": "m",
    "confidence": 0.99
}
{
    "kilometer": 0.0555,
    "inches": 2185.0393700787404,
    "feet": 182.08661417322833,
    "centimeter": 5550.0,
    "meter": 55.5,
    "miles": 0.034486090500000004,
    "yard": 60.694799999999994,
    "scalar": 55.5,
    "unit": "m",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
centimeter float distance expressed in centimeters (cm)
feet float distance expressed in feet (ft)
inches float distance expressed in inches (in)
kilometer float distance expressed in kilometers (km)
meter float distance expressed in meters (m)
miles float distance expressed in miles (ml)
yard float distance expressed in yards (yd)
scalar float source value
unit string source unit
confidence float confidence in value matching

Duration

"source":"pendant 3h",
"value":{
    "confidence": 0.99,
    "days": 0.125,
    "hours": 3,
    "minutes": 180,
    "months": 0.004166666666666667,
    "preposition": {
        "category": [
            "Localisation",
            "Duration",
            "Temporal Localisation"
        ],
        "source": "pendant"
    },
    "seconds": 10800,
    "weeks": 0.017857142857142856,
    "years": 0.00034223134839151266
}
"source":"pendant 3h",
"value":{
    "confidence": 0.99,
    "days": 0.125,
    "hours": 3,
    "minutes": 180,
    "months": 0.004166666666666667,
    "preposition": {
        "category": [
            "Localisation",
            "Duration",
            "Temporal Localisation"
        ],
        "source": "pendant"
    },
    "seconds": 10800,
    "weeks": 0.017857142857142856,
    "years": 0.00034223134839151266
}
KEY TYPE DESCRIPTION CONSTRAINTS
days float duration expressed in days
hours float duration expressed in hours (h)
minutes float duration expressed in minutes (min)
months float duration expressed in months
preposition source preposition object describes the preposition that constructs the duration
seconds float duration expressed in seconds (s)
weeks float duration expressed in weeks
years float duration expressed in years
confidence float confidence in value matching

Source Preposition Object

KEY TYPE DESCRIPTION CONSTRAINTS
category list of string see preposition categories
source string source string for the preposition

Electric Charge

{
    "Ampere-hour": 1.94444444444446e-06,
    "coulomb": 0.007,
    "Faraday": 7.254988174633501e-08,
    "elementary_charge": 4.369056752984294e+16,
    "scalar": 7.0,
    "unit": "mC",
    "confidence": 0.99
}
{
    "Ampere-hour": 1.94444444444446e-06,
    "coulomb": 0.007,
    "Faraday": 7.254988174633501e-08,
    "elementary_charge": 4.369056752984294e+16,
    "scalar": 7.0,
    "unit": "mC",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
scalar float source value
unit string source unit
confidence float confidence in value matching
Ampere-hour float electric charge expressed in ampere by hour
coulomb float electric charge expressed in Coulomb
Faraday float electric charge expressed in Faraday
elementary_charge float electric charge expressed in elementary charge

Electric Power

{
    "ampere": 0.055,
    "centiampere": 5.5,
    "kiloampere": 5.5e-05,
    "scalar": 55.0,
    "unit": "mA",
    "confidence": 0.99
}
{
    "ampere": 0.055,
    "centiampere": 5.5,
    "kiloampere": 5.5e-05,
    "scalar": 55.0,
    "unit": "mA",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
scalar float source value
unit string source unit
confidence float confidence in value matching
ampere float electric power expressed in amperes (A)
kiloampere float electric power expressed in kiloamperes (kA)
centiampere float electric power expressed in centiamperes (cA)

Energy

{
    "joule": 1231200.0,
    "MWh": 0.000342,
    "kWh": 0.342,
    "kcal": 294.067067927773,
    "toe": 2.94067067927773e-05,
    "erg": 12312000000000.0,
    "keV": 7.684546677534658e+21,
    "thm": 0.011660526390559443,
    "scalar": 342.0,
    "unit": "Wh",
    "confidence": 0.99
}
{
    "joule": 1231200.0,
    "MWh": 0.000342,
    "kWh": 0.342,
    "kcal": 294.067067927773,
    "toe": 2.94067067927773e-05,
    "erg": 12312000000000.0,
    "keV": 7.684546677534658e+21,
    "thm": 0.011660526390559443,
    "scalar": 342.0,
    "unit": "Wh",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
joule float energy expressed in joule
MWh float energy expressed in megawatt by hour
kWh float energy expressed in kilowatt by hour
kcal float energy expressed in kilocalory by hour
toe float energy expressed in tonne of oil
erg float energy expressed in erg
keV float energy expressed in kiloelectronvolt
thm float energy expressed in thm
scalar float source value
unit string source unit
confidence float confidence in value matching

Frequency

{
  "confidence": 0.99,
  "gigahertz": 1.3e-8,
  "hertz": 13,
  "kilohertz": 0.013,
  "megahertz": 0.00013,
  "scalar": 13,
  "unit": "Hz"
}
{
  "confidence": 0.99,
  "gigahertz": 1.3e-8,
  "hertz": 13,
  "kilohertz": 0.013,
  "megahertz": 0.00013,
  "scalar": 13,
  "unit": "Hz"
}
KEY TYPE DESCRIPTION CONSTRAINTS
scalar float source value
unit string source unit
confidence float confidence in value matching
hertz float frequency expressed in amperes (A)
kilohertz float frequency expressed in kiloamperes (kA)
megahertz float frequency expressed in centiamperes (cA)
gigahertz float frequency expressed in centiamperes (cA)

Fuel consumption

{
  "mpg": 9.0,
  "km/l": 3.82629336741469,
  "l/100km": 26.134953699999997,
  "km/gal": 14.484089175945241,
  "l/km": 0.26134953699999997,
  "confidence": 0.99,
  "scalar": 9,
  "unit": "mpg"
}
{
  "mpg": 9.0,
  "km/l": 3.82629336741469,
  "l/100km": 26.134953699999997,
  "km/gal": 14.484089175945241,
  "l/km": 0.26134953699999997,
  "confidence": 0.99,
  "scalar": 9,
  "unit": "mpg"
}
KEY TYPE DESCRIPTION CONSTRAINTS
mpg float fuel consumption expressed in miles per gallon
km/l float fuel consumption expressed in kilometer by liter
l/100km float fuel consumption expressed in liter by 100 kilometers
l/km float fuel consumption expressed in liter by kilometer
km/gal float fuel consumption expressed in kilometer by gallon
scalar float source value
unit string source unit
confidence float confidence in value matching

Hex Color

{
    "hex": "#FFFFFF",
    "color_name": "white",
    "rgb": {
        "blue": 255,
        "red": 255,
        "green": 255
    },
    "hsv": {
        "hue": 0,
        "value": 100,
        "saturation": 0
    },
    "hsl": {
        "hue": 0,
        "lightness": 100,
        "saturation": 0
    },
    "cmyk": {
        "yellow": 0,
        "magenta": 0,
        "cyan": 0,
        "black": 0
    }
}
{
    "hex": "#FFFFFF",
    "color_name": "white",
    "rgb": {
        "blue": 255,
        "red": 255,
        "green": 255
    },
    "hsv": {
        "hue": 0,
        "value": 100,
        "saturation": 0
    },
    "hsl": {
        "hue": 0,
        "lightness": 100,
        "saturation": 0
    },
    "cmyk": {
        "yellow": 0,
        "magenta": 0,
        "cyan": 0,
        "black": 0
    }
}

If we know about a color matching the hex color code :

KEY TYPE DESCRIPTION CONSTRAINTS
color_name string see
hex string hexadecimal representation of color
rgb RGB Object] the rgb code of the color
hsl HSL Object] the hsl code of the color
hsv HSV Object the hsv code of the color
cmyk CMJK Object the cmyk code of the color
confidence float confidence in value matching

If no matching color in database :

KEY TYPE DESCRIPTION CONSTRAINTS
hex string hexadecimal representation of color
confidence float confidence in value matching

RGB Object

RGB color model

KEY TYPE
red int
green int
blue int

HSL Object

HSL and HSV color codes

KEY TYPE
hue int
saturation int
lightness int

HSV Object

HSL and HSV color codes

KEY TYPE
hue int
saturation int
value int

CMYK Object

CMYK color model

KEY TYPE
cyan int
majenta int
yellow int
black int

Interval

"source": "demain de 13h a 17h",
"value": {
    "confidence": 0.99,
    "duration": {
        "now_end": {
            "days": 1.226400462962963,
            "hours": 29.433611111111112,
            "minutes": 1766.0166666666667,
            "months": 0.040880015432098765,
            "preposition": {
                "category": [],
                "source": null
            },
            "seconds": 105961,
            "weeks": 0.17520006613756614,
            "years": 0.0033577014728623216
        },
        "start_end": {
            "days": 0.16666666666666666,
            "hours": 4,
            "minutes": 240,
            "months": 0.005555555555555556,
            "preposition": {
                "category": [],
                "source": null
            },
            "seconds": 14400,
            "weeks": 0.023809523809523808,
            "years": 0.0004563084645220169
        },
        "start_now": {
            "days": -1.0597337962962963,
            "hours": -25.433611111111112,
            "minutes": -1526.0166666666667,
            "months": -0.03532445987654321,
            "preposition": {
                "category": [],
                "source": null
            },
            "seconds": -91561,
            "weeks": -0.15139054232804233,
            "years": -0.0029013930083403045
        }
    },
    "end": {
        "ISO": "2019-03-26 17:00:00",
        "chronology": "future",
        "chronology_day": 2,
        "confidence": 0.99,
        "formatted": "Tuesday 26 March 2019 17:00:00",
        "timestamp": 1553616000
    },
    "start": {
        "ISO": "2019-03-26 13:00:00",
        "chronology": "future",
        "chronology_day": 2,
        "confidence": 0.99,
        "formatted": "Tuesday 26 March 2019 13:00:00",
        "timestamp": 1553601600
    }
}
"source": "demain de 13h a 17h",
"value": {
    "confidence": 0.99,
    "duration": {
        "now_end": {
            "days": 1.226400462962963,
            "hours": 29.433611111111112,
            "minutes": 1766.0166666666667,
            "months": 0.040880015432098765,
            "preposition": {
                "category": [],
                "source": null
            },
            "seconds": 105961,
            "weeks": 0.17520006613756614,
            "years": 0.0033577014728623216
        },
        "start_end": {
            "days": 0.16666666666666666,
            "hours": 4,
            "minutes": 240,
            "months": 0.005555555555555556,
            "preposition": {
                "category": [],
                "source": null
            },
            "seconds": 14400,
            "weeks": 0.023809523809523808,
            "years": 0.0004563084645220169
        },
        "start_now": {
            "days": -1.0597337962962963,
            "hours": -25.433611111111112,
            "minutes": -1526.0166666666667,
            "months": -0.03532445987654321,
            "preposition": {
                "category": [],
                "source": null
            },
            "seconds": -91561,
            "weeks": -0.15139054232804233,
            "years": -0.0029013930083403045
        }
    },
    "end": {
        "ISO": "2019-03-26 17:00:00",
        "chronology": "future",
        "chronology_day": 2,
        "confidence": 0.99,
        "formatted": "Tuesday 26 March 2019 17:00:00",
        "timestamp": 1553616000
    },
    "start": {
        "ISO": "2019-03-26 13:00:00",
        "chronology": "future",
        "chronology_day": 2,
        "confidence": 0.99,
        "formatted": "Tuesday 26 March 2019 13:00:00",
        "timestamp": 1553601600
    }
}
KEY TYPE DESCRIPTION CONSTRAINTS
confidence float confidence in value matching
duration Interval Duration Object time between start, end, and present time
end Date Entity end point of the interval None if interval is open-ended
start Date Entity start point of the interval None if interval doesn't have a specified start

Interval Duration Object

KEY TYPE DESCRIPTION CONSTRAINTS
start_end Duration Entity duration between the start of the interval and its end
start_now Duration Entity duration between the start of the interval and the time of the message
now_end Duration Entity duration between the time of the message and the end of the interval

IP

[
    {
        "entity": {
            "city": "Paris",
            "hostname": "pas75-1-81-57-53-204.fbx.proxad.net",
            "lat": "48.8628",
            "lng": "2.3292",
            "country0": "FR",
            "postal": "75001",
            "region": "\u00cele-de-France",
            "ip": "81.57.53.204",
            "org": "AS12322 Free SAS",
            "confidence": 0.99
        },
        "source": "81.57.53.204",
        "tag": "ip"
    }
]
[
    {
        "entity": {
            "city": "Paris",
            "hostname": "pas75-1-81-57-53-204.fbx.proxad.net",
            "lat": "48.8628",
            "lng": "2.3292",
            "country0": "FR",
            "postal": "75001",
            "region": "\u00cele-de-France",
            "ip": "81.57.53.204",
            "org": "AS12322 Free SAS",
            "confidence": 0.99
        },
        "source": "81.57.53.204",
        "tag": "ip"
    }
]
KEY TYPE DESCRIPTION CONSTRAINTS
lat float latitude of location IP
lng float longitude of location IP
city string city of location IP
country string country ISO of location IP
postal string zipcode of location IP
region string region of location IP
hostname string name of host of location IP
org string organisation of host
ip string IP formatted
confidence float confidence in value matching

IPv6

{
    "city": "Macon",
    "lat": "32.8407",
    "lng": "-83.6324",
    "country": "US",
    "postal": "31205",
    "region": "Georgia",
    "ip": "2604:180:2::d2a1:3da5",
    "org": "AS3842 RamNode LLC",
    "confidence": 0.99
}
{
    "city": "Macon",
    "lat": "32.8407",
    "lng": "-83.6324",
    "country": "US",
    "postal": "31205",
    "region": "Georgia",
    "ip": "2604:180:2::d2a1:3da5",
    "org": "AS3842 RamNode LLC",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
lat float latitude of location IPV6
lng float longitude of location IPV6
city string city of location IPv6
country string country ISO of location IPv6
postal string zipcode of location IPv6
region string region of location IPv6
org string organisation of host
ip string IPv6 formatted
confidence float confidence in value matching

Light Intensity

{
    "candela": 7.0,
    "centicandela": 700.0,
    "kilocandela": 0.007,
    "scalar": 7.0,
    "unit": "cd",
    "confidence": 0.99
}
{
    "candela": 7.0,
    "centicandela": 700.0,
    "kilocandela": 0.007,
    "scalar": 7.0,
    "unit": "cd",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
candela float light intensity expressed in candelas (cd)
kilocandela float light intensity expressed in kilocandelas (kcd)
centicandela float light intensity expressed in centicandelas (ccd)
scalar float soure value
unit string source unit
confidence float confidence in value matching

Mail

{
    "local": "hello",
    "domain": "lettria.com",
    "confidence": 0.99
}
{
    "local": "hello",
    "domain": "lettria.com",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
local string the local part of the email
domain string the domain of the email
confidence float confidence in value matching

Mass

{
    "gramme": 4.0,
    "centigramme": 400.0,
    "kilogramme": 0.004,
    "pounds": 0.00881849768073511,
    "tonnes": 4e-06,
    "stone": 0.0006298924930987404,
    "ton": 3.936814133162738e-07,
    "onces": 0.14109596289176177,
    "scalar": 7.0,
    "unit": "g",
    "confidence": 0.99
}
{
    "gramme": 4.0,
    "centigramme": 400.0,
    "kilogramme": 0.004,
    "pounds": 0.00881849768073511,
    "tonnes": 4e-06,
    "stone": 0.0006298924930987404,
    "ton": 3.936814133162738e-07,
    "onces": 0.14109596289176177,
    "scalar": 7.0,
    "unit": "g",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
gramme float mass expressed in grams (g)
kilogramme float mass expressed in grams (kg)
centigramme float mass expressed grams in (cg)
tonnes float mass expressed in grams (t)
pounds float mass expressed in grams (lb)
stone float mass expressed in grams (st)
ton float mass expressed in grams (ton)
onces float mass expressed in grams (oz)
scalar float source value
unit string source unit
confidence float confidence in value matching

Mass by Volume

{
    "gramme/L": 33.0,
    "centigramme/L": 3300.0,
    "kilogramme/L": 0.033,
    "ton/dm3": 3.247871659859259e-06,
    "tonnes/dm3": 3.3e-05,
    "pounds/dm3": 0.07275260586606466,
    "onces/dm3": 1.1640416938570346,
    "stone/dm3": 0.005196613068064608,
    "scalar": 7.0,
    "unit": "g",
    "unit-1": "l",
    "confidence": 0.99
}
{
    "gramme/L": 33.0,
    "centigramme/L": 3300.0,
    "kilogramme/L": 0.033,
    "ton/dm3": 3.247871659859259e-06,
    "tonnes/dm3": 3.3e-05,
    "pounds/dm3": 0.07275260586606466,
    "onces/dm3": 1.1640416938570346,
    "stone/dm3": 0.005196613068064608,
    "scalar": 7.0,
    "unit": "g",
    "unit-1": "l",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
gramme/L float density expressed in grams by liters (g/L)
kilogramme/L float density expressed in kilograms by liters (kg/L)
centigramme/L float density expressed in centgrams by liters (cg/L)
tonnes/dm3 float density expressed in tonnes by cubic decimeters (t/dm3)
pounds/dm3 float density expressed in pounds by cubic decimeters (lb/dm3)
stone/dm3 float density expressed in grams (st/dm3)
ton/dm3 float density expressed in grams (ton/dm3)
onces/dm3 float density expressed in grams (oz/dm3)
scalar float source value
unit string source unit for mass
unit-1 string source unit for volume
confidence float confidence in value matching

Molar concentration

{
    "mol/L": 1000.0,
    "kmol/L": 1.0,
    "cmol/L": 100000.0,
    "mmol/L": 1000000.0,
    "μmol/L": 1000000000.0,
    "scalar": 1.0,
    "unit": "kmol",
    "unit_2": "l",
    "confidence": 0.99
}
{
    "mol/L": 1000.0,
    "kmol/L": 1.0,
    "cmol/L": 100000.0,
    "mmol/L": 1000000.0,
    "μmol/L": 1000000000.0,
    "scalar": 1.0,
    "unit": "kmol",
    "unit_2": "l",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
mol/L float concentration of substance expressed in moles by liter
kmol/L float concentration of substance expressed in kilomoles by liter
cmol/L float concentration of substance expressed in centimoles by liter
mmol/L float concentration of substance expressed in millimoles by liter
μmol/L float concentration of substance expressed in micromoles by liter
scalar float source value
unit string source mole unit
unit_2 string source volume unit
confidence float confidence in value matching

Mol

{
    "mol": 70.0,
    "centimol": 7000.0,
    "kilomol": 0.07,
    "scalar": 7.0,
    "unit": "damol",
    "confidence": 0.99
}
{
    "mol": 70.0,
    "centimol": 7000.0,
    "kilomol": 0.07,
    "scalar": 7.0,
    "unit": "damol",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
mol float amount of substance expressed in moles (mol)
kilomol float amount of substance expressed in kilomoles (kmol)
centimol float amount of substance expressed in centimoles (cmol)
scalar float source value
unit string source unit
confidence float confidence in value matching

Money

{
    "amount": 9.7,
    "ISO_code": "USD",
    "symbol": "$",
    "scalar": 9.7,
    "confidence": 0.99
}
{
    "amount": 9.7,
    "ISO_code": "USD",
    "symbol": "$",
    "scalar": 9.7,
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
amount float source value
ISO_code string ISO 4217 standard currency code
symbol string currency symbol
confidence float confidence in value matching

Ordinal

{
    "rank": 42,
    "confidence": 0.99
}
{
    "rank": 42,
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
rank int ranking of the ordinal value. First is 1
confidence float confidence in value matching

Percent

{
    "percent": 43.355,
    "scalar": 43355.0,
    "unit": "ppb",
    "confidence": 0.99
}
{
    "percent": 43.355,
    "scalar": 43355.0,
    "unit": "ppb",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
percent float percentage value expressend in percents (%, pct)
scalar float source value
unit string source unit
confidence float confidence in value matching

Phone

{
    "notation": "national",
    "country_code": "33",
    "mobile_begin": [
        "6",
        "7"
    ],
    "country_name": "France",
    "alpha_3": "FRA",
    "alpha_2": "FR",
    "phone": "607259475",
    "confidence": 0.89
}
{
    "notation": "national",
    "country_code": "33",
    "mobile_begin": [
        "6",
        "7"
    ],
    "country_name": "France",
    "alpha_3": "FRA",
    "alpha_2": "FR",
    "phone": "607259475",
    "confidence": 0.89
}
KEY TYPE DESCRIPTION CONSTRAINTS
notation string notation type ["national", "international"]
alpha_2 string the ISO 3161-1 alpha2 2 digit code of country
alpha_3 string the ISO 3161-1 alpha3 3 digit code of country
country_name string the name of the country associated to the telephone number
contry_code string the phone code of country associated to the telephone number
mobile_begin array the first digit of mobile telephone number for this country
phone int the telephone number
confidence float confidence in value matching

Power

{
    "milliwatt": 7.0,
    "Watt": 0.007,
    "kilowatt": 7e-06,
    "megawatt": 7e-09,
    "gigawatt": 7e-12,
    "scalar": 7.0,
    "unit": "mW",
    "confidence": 0.99
}
{
    "milliwatt": 7.0,
    "Watt": 0.007,
    "kilowatt": 7e-06,
    "megawatt": 7e-09,
    "gigawatt": 7e-12,
    "scalar": 7.0,
    "unit": "mW",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
milliwatt float power expressed in milliwatt
Watt float power expressed in Watt
kilowatt float power expressed in kilowatt
megawatt float power expressed in megawatt
gigawatt float power expressed in gigawatt
scalar float source unit
unit string source unit
confidence float confidence in value matching

Pressure

{
    "psi": 10.97935389,
    "Torr": 567.7969340000001,
    "scalar": 75.7,
    "millibar": 757.0,
    "pascal": 75700.0,
    "unit": "cbar",
    "atm": 0.7471007110000001,
    "bar": 0.757,
    "hectopascal": 757.0,
    "at": 0.7719129,
    "confidence": 0.99
}
{
    "psi": 10.97935389,
    "scalar": 75.7,
    "Torr": 567.7969340000001,
    "millibar": 757.0,
    "pascal": 75700.0,
    "unit": "cbar",
    "atm": 0.7471007110000001,
    "bar": 0.757,
    "hectopascal": 757.0,
    "at": 0.7719129,
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
pascal float pressure expressed in pascals (Pa)
hectopascal float pressure expressed in hectopascals (hPa)
millibar float pressure expressed in millibars (mbar)
bar float pressure expressed in bars (bar)
at float pressure expressed in technical atmospheres (at)
atm float pressure expressed in atmospheres (atm)
Torr float pressure expressed in torrs (Torr)
psi float pressure expressed in pounds per square inches (psi)
scalar float source unit
unit string source unit
confidence float confidence in value matching

Radioactivity

{
    "MBq": 2590000000.0,
    "GBq": 259000000000000.0,
    "Rd": 259000000.0,
    "Ci": 7000.0,
    "kCi": 7.0, 
    "scalar": 7.0,
    "unit": "kCi",
    "confidence": 0.99
}
{
    "MBq": 2590000000.0,
    "GBq": 259000000000000.0,
    "Rd": 259000000.0,
    "Ci": 7000.0,
    "kCi": 7.0, 
    "scalar": 7.0,
    "unit": "kCi",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
MBq float radioactivity expressed in megaBecquerel
GBq float radioactivity expressed in gigaBecquerel
Rd float radioactivity expressed in Rutherford
Ci float radioactivity expressed in Curie
kCi float radioactivity expressed in kiloCurie
scalar float source unit
unit string source unit
confidence float confidence in value matching

Set

"source":"tous les jours",
"value":{
    "confidence": 0.99,
    "start": {
        "ISO": "2019-03-26 11:23:05",
        "chronology": "future",
        "chronology_day": 2,
        "formatted": "Tuesday 26 March 2019 11:23:05",
        "timestamp": 1553595785
    },
    "step": {
        "day": 1,
        "hour": 24,
        "minute": 1440,
        "month": 0.03333333333333333,
        "seconde": 86400,
        "week": 0.14285714285714285,
        "year": 0.0027378507871321013
    }
}
"source":"tous les jours",
"value":{
    "confidence": 0.99,
    "start": {
        "ISO": "2019-03-26 11:23:05",
        "chronology": "future",
        "chronology_day": 2,
        "formatted": "Tuesday 26 March 2019 11:23:05",
        "timestamp": 1553595785
    },
    "step": {
        "day": 1,
        "hour": 24,
        "minute": 1440,
        "month": 0.03333333333333333,
        "seconde": 86400,
        "week": 0.14285714285714285,
        "year": 0.0027378507871321013
    }
}
KEY TYPE DESCRIPTION CONSTRAINTS
start Date Entity first occurence of in the set always in the future
step Set Step Object time between two occurences in the set
confidence float confidence in value matching

Set Step Object

KEY TYPE DESCRIPTION CONSTRAINTS
day float
hour float
minute float
month float
second float
week float
year float

Speed

{
    "km/h": 120.0,
    "m/s": 33.333333333333336,
    "kts": 64.79484,
    "mph": 74.56452,
    "scalar": 120.0,
    "unit": "km",
    "confidence": 0.99
}
{
    "km/h": 120.0,
    "m/s": 33.333333333333336,
    "kts": 64.79484,
    "mph": 74.56452,
    "scalar": 120.0,
    "unit": "km",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
m/s float speed expressed in meters per second (m/s)
km/h float speed expressed in kilometers per hour (km/h)
mph float speed expressed in miles per hour (mph)
kts float speed expressed in knots (kn, kts)
scalar float source value
unit string source unit
confidence float confidence in value matching

Strength

{
    "newton": 70.0,
    "centinewton": 7000.0,
    "kilonewton": 0.07,
    "scalar": 7.0,
    "unit": "daN",
    "confidence": 0.99
}
{
    "newton": 70.0,
    "centinewton": 7000.0,
    "kilonewton": 0.07,
    "scalar": 7.0,
    "unit": "daN",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
newton float force expressed in newton
kilonewton float force expressed in kilonewton
centinewton float force expressed in centinewton
scalar float source value
unit string source value
confidence float confidence in value matching

Surface

{
    "meter": 43000.0,
    "centimeter": 430000000.0,
    "kilometer": 0.043,
    "hectares": 4.3,
    "inches": 66650000.0,
    "miles": 0.0166023,
    "ares": 430.0,
    "scalar": 4.3,
    "unit": "ha",
    "confidence": 0.99
}
{
    "meter": 43000.0,
    "centimeter": 430000000.0,
    "kilometer": 0.043,
    "hectares": 4.3,
    "inches": 66650000.0,
    "miles": 0.0166023,
    "ares": 430.0,
    "scalar": 4.3,
    "unit": "ha",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
meter float surface expressed in square meters (m²)
kilometer float surface expressed in square kilometers (km²)
centimeter float surface expressed in square centimeters (cm²)
miles float surface expressed in square miles (mi²)
ares float surface expressed in ares
hectares float surface expressed in hectares
inches float surface expressed in square inches (in²)
scalar float source value
unit string source unit
confidence float confidence in value matching

Surface Tension

{
    "N/centimeter": 20.0,
    "N/meter": 0.2,
    "N/kilometer": 0.0002,
    "scalar": 2.0,
    "unit": "dm",
    "confidence": 0.99
}
{
    "N/centimeter": 20.0,
    "N/meter": 0.2,
    "N/kilometer": 0.0002,
    "scalar": 2.0,
    "unit": "dm",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
N/meter float surface tension expressed in newtons per meter (N/m)
N/kilometer float surface tension expressed in newtons per kilometer (N/km)
N/centimeter float surface tension expressed in newtons per centimeter (N/cm)
scalar float source value
unit string source unit
confidence float confidence in value matching

Temperature

{
    "rankine": 559.17,
    "fahrenheit": 99.5,
    "kelvin": 310.65,
    "celsius": 37.5,
    "scalar": 37.5,
    "unit": "C",
    "confidence": 0.99
}
{
    "rankine": 559.17,
    "fahrenheit": 99.5,
    "kelvin": 310.65,
    "celsius": 37.5,
    "scalar": 37.5,
    "unit": "C",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
celsius float temperature expressed in Celsius (°C)
fahrenheit float temperature expressed in Fahrenheit (°F)
kelvin float temperature expressed in Kelvin (K)
rakine float temperature expressed in Rakine (°R)
scalar float source value
unit string source unit
confidence float confidence in value matching

Time

{
    "ISO": "5:30",
    "formatted": "datetime.time(5, 30)",
    "chronology": "past",
    "chronology_min": 745,
    "confidence": 0.99
}
{
    "ISO": "5:30",
    "formatted": "datetime.time(5, 30)",
    "chronology": "past",
    "chronology_min": 745,
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
ISO string ISO formatted time hh:mi
formatted string time written in english
chronology string if time is: future / past or present
chronology_min int number minute in diff time with present
confidence float confidence for this entitie

URL

{
    "sheme": "https",
    "fragment": null,
    "query": "love=you",
    "host": "man.lettria.com",
    "confidence": 0.99
}
{
    "sheme": "https",
    "fragment": null,
    "query": "love=you",
    "host": "man.lettria.com",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
sheme string the URL scheme (http/https/ssh..)
fragment string The anchor of the URL
query string The query parameters of the URL
host string Tthe host of the URL
confidence float confidence for this entitie

Voltage

{
    "volt": 70.0,
    "centivolt": 7000.0,
    "kilovolt": 0.07,
    "scalar": 7.0,
    "unit": "daV",
    "confidence": 0.99
}
{
    "volt": 70.0,
    "centivolt": 7000.0,
    "kilovolt": 0.07,
    "scalar": 7.0,
    "unit": "daV",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
volt float voltage expressed in volts (V)
kilovolt float voltage expressed in kilovolts (kV)
centivolt float voltage expressed in centivolts (cV)
scalar float source value
unit string source unit
confidence float confidence in value matching

Volume

{
    "milliliter": 43000.0,
    "meter": 0.043,
    "feet": 1.518545,
    "miles": 1.033079195851154e-11,
    "kilometer": 4.3e-11,
    "teaspoon": 8724.02067795785,
    "inches": 2624.0191,
    "liter": 43.0,
    "tablespoon": 2908.0068926526164,
    "centimeter": 43000.0,
    "gallon": 11.359396,
    "decimeter": 43.0,
    "yard": 0.05624185,
    "scalar": 43.0,
    "unit": "dm",
    "confidence": 0.99
}
{
    "milliliter": 43000.0,
    "meter": 0.043,
    "feet": 1.518545,
    "miles": 1.033079195851154e-11,
    "kilometer": 4.3e-11,
    "teaspoon": 8724.02067795785,
    "inches": 2624.0191,
    "liter": 43.0,
    "tablespoon": 2908.0068926526164,
    "centimeter": 43000.0,
    "gallon": 11.359396,
    "decimeter": 43.0,
    "yard": 0.05624185,
    "scalar": 43.0,
    "unit": "dm",
    "confidence": 0.99
}
KEY TYPE DESCRIPTION CONSTRAINTS
decimeter float volume expressed in cubic decimeters (dm³)
meter float volume expressed in cubic meters (m³)
kilometer float volume expressed in cubic kilometers (km³)
centimeter float volume expressed in cubic centimeters (cm³)
miles float volume expressed in cubic miles (mi³)
inches float volume expressed in cubic inches (in³)
feet float volume expressed in cubic feet (ft³)
yard float volume expressed in cubic yards (yd³)
gallon float volume expressed in gallons (gal)
teaspoon float volume expressed in teaspoons (tsp)
tablespoon float volume expressed in tablespoons (tp)
liter float volume expressed in liters (L)
milliliter float volume expressed in milliliters (mL)
scalar float source value
unit string source unit
confidence float confidence in value matching

Categories

List of all categories that can be found in Category Objects. Categories are organised by super-categories, each containing a number of sub-categories.

For instance, the super-category 'PERSON' contains categories like 'soldier', 'firstname', or even 'slavic_divinity' alongside many others !

The full list of categories is split between the verbs, nouns, adjectives, adverbs, prepositions and interjections.

Category Object

This object can be found in NLU, parser_dependency, and synthesis.

KEY TYPE DESCRIPTION CONSTRAINTS
super string the super-category UPPER_CASE
sub string the sub-category lower_case
extra string extra information about the category -
derivates string indicates that the category corresponds to another part of speech tag see tags
intensity float intensity, mostly for adjectives and adverbs -

Verb categories

SUPER SUB EXAMPLES
ACTION action_draw esquisser, recrire, colorer, peindre
ACTION action_round entourer, cerner, ceinturer, encercler
ACTION action_hurt poignarder, blesser, defigurer, decapiter
ACTION action_prevent brider, empecher, exonerer, retenir
ACTION action_speak begayer
ACTION action_break fouler, decouper, dissiper, eclater
ACTION action_add accoler, rassembler, accroitre, engranger
ACTION action_call rappeler, prenommer, contacter, nommer
ACTION action_live resider, exister, vivre, autoheberger
ACTION action_open rouvrir
ACTION action_fake fausser, pretendre, simuler, sophistiquer
ACTION action_kiss becoter, baisoter, baiser, embrasser
ACTION action_play divertir, badiner, blaguer, amuser
ACTION action_think considerer, elaborer, penser, studier
ACTION action_bloom eclore, bourgeonner, developper, epanouir
ACTION action_get_fat arrondir, epaissir, bouffir, alourdir
ACTION action_ask interroger, intimer, mendier, solliciter
ACTION action_sort arranger, repartir, cataloguer, ordonner
ACTION action_meet frequenter, accoster, rencontrer, rejoindre
ACTION action_move gambader, migrer, voleter, gigoter
ACTION action_shoot tirer, canarder
ACTION action_kill assommer, immoler, executer, lapider
ACTION action_turn ronder, bifurquer, tourner, orbiter
ACTION action_hit assommer, matraquer, choquer, jaber
ACTION action_take_care flatter, dorloter, chouchouter, cajoler
ACTION action_strike heurter
ACTION action_die trepasser, succomber, crever, deceder
ACTION action_innovate etrenner, lancer, innover, inventer
ACTION action_ban oter, censurer, repudier, supprimer
ACTION action_suffer peiner, souffrir, baver, subir
ACTION action_copy mimer, couper-coller, singer
ACTION action_bring emporter, rapporter, raccompagner, rapatrier
ACTION action_fire limoger
ACTION action_hidden cacher, envelopper, couvrir, ensevelir
ACTION action_can pouvoir
ACTION action_translate traduire, transcrire, decrypter, transcoder
ACTION action_warm rechauffer
ACTION action_search visiter, examiner, scruter, chercher
ACTION action_plug embrancher, connecter, brancher
ACTION action_cut decouper
ACTION action_destroy briser, dechiqueter, abattre, fracasser
ACTION action_read bouquiner, feuilleter, relire, lire
ACTION action_miss rater, louper, manquer
ACTION action_keep sauvegarder, garder
ACTION action_damage elimer, casser, infecter, scarifier
ACTION action_refine epurer, ecremer, assainir, decoudre
ACTION action_sell vendre, ecouler, revendre, retroceder
ACTION action_hate maudire
ACTION action_walk balader, deambuler, vagabonder, pietiner
ACTION action_try tenter, intenter, attenter, oser
ACTION action_flow couler, coulisser, glisser, mouvoir
ACTION action_learn renseigner, enseigner, informer, reapprendre
ACTION action_force brusquer, precipiter, astreindre, imposer
ACTION action_shine flamboyer, luire, aveugler, eblouir
ACTION action_train echauffer, courbaturer
ACTION action_expel expulser, eliminer, rejeter, refouler
ACTION action_end resulter, cloturer, enteriner, finir
ACTION action_share distribuer, partager, compartir, separer
ACTION action_hire employer, recruter, embaucher, embrigader
ACTION action_heal soulager, soigner, strapper, retablir
ACTION action_smash heurter
ACTION action_control verifier, controler, superviser, patrouiller
ACTION action_laugh plaisanter, rire, egayer, divertir
ACTION action_light eclairer, enflammer, embraser, incendier
ACTION action_allow autoriser, permissionner, permettre
ACTION action_attack buter, taillader, defigurer, assaillir
ACTION action_decrease abaisser, regresser, deprecier, rabaisser
ACTION action_cross croiser, transiter, entrecroiser
ACTION action_drive vehiculer, acheminer, transporter, debrayer
ACTION action_reward primer, remunerer, recompenser, gratifier
ACTION action_accept valider, enteriner, approuver, comprendre
ACTION action_have reprendre, appartenir, detenir, beneficier
ACTION action_starsh amidonner
ACTION action_relax detendre, etendre, delasser, adoucir
ACTION action_detect percevoir, apercevoir, detecter, devoiler
ACTION action_ring alerter, carillonner, claironner, sonnailler
ACTION action_grow grossir, grandir, cultiver, murir
ACTION action_describe detailler, depeindre, decrire
ACTION action_mix remixer, brouiller, emmeler, entrecroiser
ACTION action_stop barrer, suspendre, clore, barricader
ACTION action_create naitre, recreer, fabriquer, improviser
ACTION action_throw relancer, balancer, lancer, catapulter
ACTION action_stay eterniser, resider, domicilier, loger
ACTION action_build batir
ACTION action_get beneficier, posseder, avoir, reprendre
ACTION action_cheer stimuler, conforter, enhardir, encourager
ACTION action_manufacture mouler, emplatrer, teinter, sculpter
ACTION action_cover etaler, recouvrir
ACTION action_steal carotter, piquer, escroquer, rafler
ACTION action_come intervenir, arriver, reunir, rendre
ACTION action_name surnommer, prenommer, denommer, mentionner
ACTION action_select preferer, elire, retenir, adopter
ACTION action_dress rhabiller, boutonner, revetir, vetir
ACTION action_do_business marchander, bazarder, brocanter, vendre
ACTION action_teach demontrer, instruire, inculquer, professer
ACTION action_lie fabuler, mentir, desinforme, affabuler
ACTION action_climb gravir
ACTION action_buy obtenir, acquerir, consommer, devaliser
ACTION action_scare intimider, effaroucher, epouvanter, violenter
ACTION action_split disloquer, quitter, divorcer, sectionner
ACTION action_win renverser, triompher, maitriser, vaincre
ACTION action_touch toucher, affleurer, piquer, palper
ACTION action_attract plaire, racoler, importer, attirer
ACTION action_work bricoler, operer, produire, travailler
ACTION action_turn_on brancher
ACTION action_develop cultiver, pousser, developper, etendre
ACTION action_free amnistier, acquitter, liberer
ACTION action_clean restaurer, eponger, decaper, deterger
ACTION action_do executer, perpetrer, oeuvrer, operer
ACTION action_dislike indisposer, denigrer, importuner, repugner
ACTION action_save rememorer, defendre, emmagasiner, coffrer
ACTION action_code encoder, crypter, debuguer, webiser
ACTION action_like complaire, plaire, acclamer, liker
ACTION action_support sponsoriser
ACTION action_understand acquiescer, confirmer, agreer, approuver
ACTION action_manipulate pieger
ACTION action_need necessiter, falloir, devoir
ACTION action_feed ravitailler, engaver, alimenter, allaiter
ACTION action_fool parodier, arnaquer, baratiner, tricher
ACTION action_swim baigner, crawler
ACTION action_fear paniquer, angoisser
ACTION action_warn signaler, avertir, prevenir, alerter
ACTION action_run detaler, regaloper, cavaler, decaniller
ACTION action_store engranger, congeler, classer
ACTION action_disturb encombrer, entraver, indisposer, titiller
ACTION action_eat ingerer, petit-dejeuner, bouffer, nourrir
ACTION action_explain depeindre, eclaircir, expliquer, epiloguer
ACTION action_put etaler, mettre, amener, placer
ACTION action_increase croitre
ACTION action_weaken relacher, amenuiser, degrader, diminuer
ACTION action_give conferer, administrer, gater, verser
ACTION action_cheat falsifier, truquer, filouter, truander
ACTION action_see percevoir, visualiser, voir, visiter
ACTION action_say indiquer, marcher, annoncer, chanter
ACTION action_punish sanctionner, punir, sevir, verbaliser
ACTION action_help reconforter, collaborer, aider, depanner
ACTION action_know connaitre, reconnaitre, savoir
ACTION action_spend flamber, debourser, dilapider, payer
ACTION action_burn enflammer, braiser, consumer, embraser
ACTION action_fight embrouiller, batailler, assaillir, objecter
ACTION action_show paraitre, exhiber, exposer, apparaitre
ACTION action_feel apprecier, notifier, discerner, ressentir
ACTION action_lock ecrouer, confiner, cadenasser, sequestrer
ACTION action_invite solliciter, recevoir, convier, inviter
ACTION action_plan projeter, preparer, prevoir, premediter
ACTION action_replicate photocopier, repliquer, recopier, calquer
ACTION action_cost valoir, chiffrer, couter
ACTION action_upset chahuter, bouleverser, affecter, emotionner
ACTION action_cry pleurer, chialer
ACTION action_smell sentir, embaumer
ACTION action_catch rattraper, attacher, capter, capturer
ACTION action_paste couper-coller
ACTION action_trust fier
ACTION action_twist tordre, demettre, fouler, deboiter
ACTION action_write noter, inscrire, gribouiller, rediger
ACTION action_take accaparer, emparer, prendre, rafler
ACTION action_let autoriser, consentir, laisser, permettre
ACTION action_slow freiner, diminuer, ralentir
ACTION action_protest debattre, affronter, tempeter, rebeller
ACTION action_solve traiter, resoudre, conclure, solutionner
ACTION action_hold brider, retenir, recuperer, avoir
ACTION action_push broyer, pusher, desequilibrer, emboutir
ACTION action_rely_on dependre
ACTION action_love plaire
ACTION action_choose arbitrer, correspondre
ACTION action_protect proteger, garantir, sauver, recueillir
ACTION action_remember souvenir
ACTION action_hear assister, comprendre, assimiler, eveiller
ACTION action_rain pleuvoter, pleuvoir, pleuvioter, neiger
ACTION action_hide occulter, eclipser, deguiser, cacher
ACTION action_fix recoudre, restaurer, guerir, repeindre
ACTION action_jump sursauter, sauter
ACTION action_locate installer, positionner, situer, orienter
ACTION action_start recommencer, commencer, entamer, initialiser
ACTION action_yell galvaniser, gueuler, engueuler, rugir
ACTION action_disappoint decevoir
ACTION action_flee enfuir, fuir, decamper, sauver
ACTION action_blame blamer, medire, detracter, reprocher
ACTION action_cook saupoudrer, zester, cuisiner, cuminer
ACTION action_close occlure, refermer, fermer, reclore
ACTION action_divide dissequer
ACTION action_guess depister, flairer, soupconner, pressentir
ACTION action_happen arriver, operer, survenir
ACTION action_stock amasser, emmagasiner, entreposer, entasser
ACTION action_delay retarder, encombrer, embouteiller, reporter
ACTION action_send mandater, communiquer, expedier, transfuser
ACTION action_forget omettre, oublier
ACTION action_broadcast live-twitter, sous-mediatiser, diffuser, surmediatiser
ACTION action_hurry accelerer, depecher, brusquer, precipiter
ACTION action_shake gigoter, brouiller, agiter, convulser
ACTION action_fall sombrer, ecrouler, affaisser, chuter
ACTION action_pull attirer, soutirer, tirer, trainer
ACTION action_hug resserrer, serrer, etreindre, enlacer
ACTION action_squeeze presser, emmailloter, compresser, appuyer
ACTION action_unlock debloquer
ACTION action_brag frimer, coqueter, rengorger, exagerer
ACTION action_surprise consterner, estomaquer, interloquer, surprendre
ACTION action_link amalgamer, allier, rassembler, synchroniser
ACTION action_watch surveiller, mater, zoomer, vigiler
ACTION action_entertain divertir
ACTION action_pee pissouiller, pissoter, uriner, pisser
ACTION action_enjoy delecter, jouir, beneficier, profiter
ACTION action_erase effacer, supprimer, disparaitre, gommer
ACTION action_sing chanter, roucouler, fredonner, bercer
ACTION action_dream fantasmer, extravaguer, planer, songer
ACTION action_change devenir, rapetisser, remplacer, osciller
ACTION action_dominate vaincre, dominer, regir, assouvir
ACTION action_make confectionner, accomplir, effectuer, produire
ACTION action_rest delasser, dormailler, sommeiller, remettre
ACTION action_fly planer
ACTION action_refuse decliner
ACTION action_exhaust abattre, exceder, harceler, lasser
ACTION action_drink siroter, bourrer, boire, pinter
ACTION action_manage administrer, gerer, manier, reussir
ACTION action_get_angry irriter, rager, horripiler, agacer
ACTION action_find degoter, trouver, retrouver
ACTION action_lead mener, dicter, chaperonner, commander
ACTION action_led conceder
ACTION action_hunt dejucher, depister, braquer, traquer
ACTION action_pray prier, agenouiller, communier, conjurer
ACTION action_hope desirer, escompter, presumer, aspirer
ACTION action_lose abdiquer, perdre, egarer, louper
ACTION action_release mourir, sacrifier, abandonner, lacher
ACTION action_joke chambrer, amuser, plaisanter, charrier
ACTION action_sleep rever, roupiller, sommeiller, coucher
ACTION action_wait attarder, attendre, patienter, suspendre
ACTION action_bore poireauter, exceder, embeter, assommer
ACTION action_worry tracasser, ronger, soucier, preoccuper
ACTION action_precede auto-anterioriser, preluder, prefacer, preceder
ACTION action_want desirer, adorer, reclamer, convoiter
ACTION action_count chiffrer, compter, recompter
ACTION action_talk commenter, discourir, jacasser, renseigner
ACTION action_undress decouvrir, debotter, devetir, denuder
ACTION action_be etre, revivre, redevenir, habiter
SENTIMENT sentiment_surprise choquer, consterner, desarconner, interloquer
SENTIMENT sentiment_disgust rebuter, ecoeurer, indisposer, degouter
SENTIMENT sentiment_protest tempeter, revolter, pester, protester
SENTIMENT sentiment_worry inquieter, troubler, soucier, tracasser
SENTIMENT sentiment_enjoy regaler, jubiler, delecter, deguster
SENTIMENT sentiment_bad denigrer, critiquer, decrier, gueuler
SENTIMENT sentiment_disappoint desenchanter, desoler, frustrer, desappointer
SENTIMENT sentiment_suffer eprouver, souffrir, patir, baver
SENTIMENT sentiment_hate execrer, maudire, detester, vomir
SENTIMENT sentiment_laugh plaisanter, divertir, blaguer, bidonner
SENTIMENT sentiment_dislike rebuter, offusquer, mecontenter, importuner
SENTIMENT sentiment_joke chambrer
SENTIMENT sentiment_upset bouleverser, affecter, ebranler
SENTIMENT sentiment_love admirer, aimer, favoriser, raffoler
SENTIMENT sentiment_anger rouspeter
SENTIMENT sentiment_like acclamer, apprecier, liker, complaire
SENTIMENT sentiment_attract attirer, charmer, plaire
SENTIMENT sentiment_fear paniquer, angoisser
SENTIMENT sentiment_bore embeter, ennuyer, assommer, accabler

Noun categories

Each noun can have one or more categories in which it belongs. Categories are themselves grouped up in Super-categories. Code for language categories follows ISO 639-1.

SUPER SUB EXAMPLES
PERSON informal_demonym tico, zemmour, portos, vosgepatte
PERSON mayan_divinity xmucane, serpent-vision, chac, monstre witz
PERSON profession_healthcare oculiste, neurologiste, neurologue, oculariste
PERSON berber_divinity dii mauri, anzar, agurzil, amon
PERSON super_hero captain america, wonderwoman, robin, spiderman
PERSON firstname maurad, alvino, tany, anousack
PERSON tibetan_buddhist_divinity maitreya, vajra varahi, kalarupa, vajrakilaya
PERSON greek_divinity Érotes, athena, adonis, phorcys
PERSON ethnonym saint-jacquins, riceton, deodatiens, lichosienne
PERSON polynesian_divinity tinilau, tangaroa, pele, tama-nui-te-rā
PERSON voodoo_divinity damballa, ayida wedo, ogun, grand bois
PERSON roman_divinity anna perenna, morpheus, proserpine, bacchus
PERSON gladiator fortus, essedaire, samnite, andabate
PERSON athlete decathlonien, arbitre, funambule, kayakiste
PERSON profession_catering barista, cafetier, serveur, saucier
PERSON collector cervalabelophile, chelonephile, fabophilie, ferrovipathe
PERSON gallic_divinity nantosuelte, damona, sucellos, vesunna
PERSON profession_criminal narcotrafiquant, baron de la drogue, sequestreur, bootlegger
PERSON musician vocalisateur, flutiste, basse, concertiste
PERSON hero belle au bois dormant, don quichotte, achille talon, dingo
PERSON egyptian_divinity singe-qefdenou, nekheb-kaou, taa, sept hathor
PERSON military_rank caporal, lieutenant-general, lieutenante, sergent-chef
PERSON chinese_divinity zhong kui, manjushri, wenchangdijun, baoshengdadi
PERSON profession_sales teleacteur, commercial, gourlier, maroquinier
PERSON gender_identity transsexuel, genre, merm, intersexuation
PERSON profession_science parasitologiste, geobiologiste, semanticien, cryptographe
PERSON incan_divinity axomama, pachamama, mama ocllo, mama quilla
PERSON aztec_divinity quetzalcoatl, xochipilli, tepeyollotl, huitzilopochtli
PERSON irish_divinity goibniu, oengus, lug, dana
PERSON profession_education pion, principal, conseiller principal de education, garde en milieu familial
PERSON mesopotamian_divinity anunnaki, ninazu, pazuzu, tiamat
PERSON soldier franc-tireur, mp, samurai, kamikaze
PERSON family remps, reum, tata, maman
PERSON nordic_divinity mani, delling, skuld, yngvi
PERSON hindu_divinity yama, bhairavi, lingam, ganga
PERSON faith carmelite, bonze, dalai lama, bulliste
PERSON japanese_divinity zuijin, ohoyamatsumi, hārītī, hitorigami
PERSON lordship principat, woiwodie, archiduche, vicomte
PERSON profession pleban, massicotier, peintre, onomasiologue
PERSON profession_law maton, assistant juridique, inspecteur general, grapignan
PERSON informal_ethnonym chinoir, bride, bamboula, pied-tendre
PERSON slavic_divinity rod, vesna, rojanice, svarog
VEGETAL fibre_plants ramie, kapokier, cotonnier, sisal
VEGETAL lichen tamier, morelle faux jasmin, tamier commun, bignone orchidee
VEGETAL fruit_tree arbre a pain, citronnier des quatre saisons, pruneautier, figuier domestique
VEGETAL vine oreille-d abbe, cotyledon, orpin, petite joubarbe
VEGETAL medicinal_herb pavot jaune, euphorbe maritime, soude brulee, obione faux-pourpier
VEGETAL succulent pteride, doradille du jura souabe, ceterach, fougere-aigle
VEGETAL toxic_plant cestreau nocturne, cigue de athenes, hepatique des jardins, ache
VEGETAL aromatic_plant pilocere, cactus a raquette, oponce, cactus raquette
VEGETAL alpine_plant haricot de mer, nori, varech, fucus
VEGETAL plant_family ambroisie, petite marguerite, centauree du solstice, raisin de amerique
VEGETAL flower lamiacees, lythracees, celastracees, convolvulacees
VEGETAL conifers jussie a petites fleurs, ceratophylle inerme, cornifle submerge, viorne aquatique
VEGETAL fern dahlia arborescent, ancolie, liseron des monts cantabriques, goutte-de-sang
VEGETAL oleaginous_plant moss, polytrichum, mousse, sphaigne
VEGETAL creeper houblon, clematite brulante, vigne, rosier toujours vert
VEGETAL invasive_plant romarin, pouliot, farigoule, lavande male
VEGETAL cacti saksaoul, castanopside a feuilles dorees, pin, olivier sauvage
VEGETAL waterside_plant peltigere, orseille, usnee, cladonie
VEGETAL aquatic_plant violette des haies, herbe aux chamois, orchis moucheron, nigritelle de rellikon
VEGETAL poplar sapin de norvege, cedre du liban, cedre, genevrier cade
VEGETAL grape_variety negrette de toulouse, gouais, beclan, morillon
VEGETAL tree osier des vanniers, saule, verdiau, saule tortueux
VEGETAL willow tremble, liard, peuplier blanc, peuplier commun
VEGETAL ornamental_plant pommier de carthage, bignone rose, sapin de norvege, hibiscus de chine
VEGETAL moss pensee des champs, souci sauvage, tormentille, garance
FOOD/DRINK dough pate sablee, pate a choux, pate a chou, pate brisee
FOOD/DRINK meat minerai de viande, magret, merguez, canard
FOOD/DRINK pizza reine, marinara, vegetarienne, stromboli
FOOD/DRINK drink scotch, rhum industriel, expresso, citronnelle
FOOD/DRINK edible_plant figuier de barbarie, couscounille, cousteline, vesce craque
FOOD/DRINK wine vin rose, clos-vougeot, montrachet, rouquin
FOOD/DRINK legume gramme vert, gesse pois chiche, astragale de montpellier, vesce commune
FOOD/DRINK vegetable artichaut de jerusalem, crosne, zucchini, radis noir
FOOD/DRINK cheese caravane, livarot, munster, comte
FOOD/DRINK condiment olivete, noix de terre, cive, romarin
FOOD/DRINK cocktail kir royal, ti-punch, kir, mauresque
FOOD/DRINK confectionery chamallow, whippet, confeito, grisette
FOOD/DRINK viennoiserie pain au chocolat, couque au chocolat, petit pain au chocolat, petit pain
FOOD/DRINK spice vanille, clou de girofle, muscade, sansho
FOOD/DRINK seafood mollusque, modiole, moule bleue, cerithe
FOOD/DRINK potato pomme de terre de conservation, vitelotte, agata, pompadour
FOOD/DRINK food_course matza, taco, raclette, gnamacoudji
FOOD/DRINK cereal sesame, riz rond, avoine, seigle
FOOD/DRINK cake/dessert palmier, gateau de fete, massepain, kouign-amann
FOOD/DRINK citrus kalamansi, clemenvilla, lime, citron
FOOD/DRINK fruit cinelle, piridion, cheche, banane
FOOD/DRINK pasta macaroni, demi-lune, penne, croziflette
FOOD/DRINK mushroom argouane, truffe noire du perigord, charbonnier, fuliginees
ANIMAL mustelid loutre de mer, carcajou, enhydre, loutre
ANIMAL marsupial myrmecobie a bandes, rat-kangourou du desert, tigre de tasmanie, sarigue de amerique du nord
ANIMAL worm ascaridide, ver de fumier, gordius, escavene
ANIMAL spider mygale, araignee-crabe, babouk, latrodecte
ANIMAL imaginary_animal qilin, cochon-garou, chante-clair, drac
ANIMAL seal otarie, ours marin, lion de mer, otarie a criniere
ANIMAL equine takhi, paleotherium, anesse, ane sauvage
ANIMAL monkey singe de le ancien monde, singes verts de savane, gibbon de hainan, guenuche
ANIMAL chicken bourbonnaise, bresse, poule de pavilly, combattant indien
ANIMAL ovine mouflon du canada, vassive, belier, ovin
ANIMAL snake bitis, acontias, taipan, crotale
ANIMAL antelope antilope-chevreuil, kob commun, oryx a cou roux, rhebuck
ANIMAL elephantidae elephant de afrique, elephantide, elephant de asie, stegodon
ANIMAL insect pou du mouton, bombyx du murier, calosome, cheval du bon dieu
ANIMAL cephalopod supion, seiche, teuthide, calmar colossal
ANIMAL mite aoutat, mite, ciron, trombidion
ANIMAL bird sturnide, grive drenne, tyran tritri, texan
ANIMAL pig blanc de le ouest, porc basque, grand porc rouge anglais, cochon nain
ANIMAL dinosaure panphagia protos, jaklapallisaurus, bagaceratops, bellusaurus sui
ANIMAL amphibian ambystome tigre, pelobate, grenouille de perez, salamandre noire
ANIMAL cornivore cochon de mer, chien-rat, civette africaine, civette
ANIMAL mollusc minard, pinnier, petoncle, bec-de-jar
ANIMAL turtle tortue des marais, tortue, tortue a oreillons jaunes, courte-queue
ANIMAL squirrel ecureuil commun, ecureuil de eurasie, spermophile citille, polatouche
ANIMAL mammal herisson de algerie, musaraigne alpine, musaraigne des champs, musaraigne naine
ANIMAL dog coban kopegi, braque francais, retriever du labrador, fila brasileiro
ANIMAL rhinoceros rhino, rhinoceron, rhinoceros de java, rhinoceros
ANIMAL rodent cochon de inde, bobak de mongolie, souris domestique, rat brun sauvage
ANIMAL alternative_name_of_animal clebs, chien, goel, cracou, minette
ANIMAL canid chacal a flancs rayes, lycaon, renard polaire, chacal a dos noir
ANIMAL cnidarian actinie verte, sertulaire, abrotanoide, anemone beignet
ANIMAL cervidae cerf porte-musc, daim de perse, chevrillard, cerf rouge
ANIMAL hippopotamus hippopotame commun, hippopotame africain, hippopotame amphibie, hippopotame
ANIMAL rabbit hermine, havane francais, neo-zelandais, hollandais
ANIMAL lizard seps tridactyle, trapele, basilic, rasiette
ANIMAL bat_animal rhinolophe vrai, fer a cheval, grand fer a cheval, minioptere
ANIMAL animal_baby hirondeau, aiglonne, pigeonneau, eterle
ANIMAL giraffidae girafon, girafeau, girafe, giraffe
ANIMAL bird_of_prey autour des moluques, aigle a tete blanche, busard fluviatile, vautour fauve
ANIMAL feline tigrillon, chat de jungle, lynx pard, lionceau
ANIMAL crustacean squille, podocere, piade, chalime
ANIMAL unicellular_organism globigerine, noctiluque, theileria, paramecie
ANIMAL cat chat, chantilly-tiffany, maine coon, golden shaded
ANIMAL gastropod escargot turc, turritelle commune, patelle bleue, gros-gris
ANIMAL lemur lepilemur, lemuriformes, maki catta, indri
ANIMAL camelid alpaga, chameaux, vaisseau du desert, paco
ANIMAL bovine andalouse grise, sheko, bufflone, bovin de limpurg
ANIMAL ursidae ours polaire, ourson, ours brun, urside
ANIMAL parrot/budgie lori arlequin, conure a tete de or, loriquet a tete bleue, toui de spix
ANIMAL mythological_creature dragonneau, strige, sirene des eaux, leviathan
ANIMAL marine_mammal dauphin, rorqual, baleine a bec commune, nordcaper
ANIMAL fish serran commun, gorette, gouanie, daurade grise
ANIMAL butterfly ecaille pourpree, phalene ocellee, cidarie a bandes vertes, lichenee
ANIMAL porcin potamochere, sanglier geant, marcassin, quartanier
ANIMAL goat pyrenees, golden guernsey, chevre des grisons a rayures, girgentana
ANIMAL sheep lincoln, corse, romanov, tarasconnaise
ANIMAL bivalve bucarde a papilles, anomie pelure-d’oignon, gallinette, clovisse doree
ANIMAL horse welsh, akal teke, cheval percheron, poney shetland
ANIMAL crocodile alligator, deinosuchus, gavial, crocodile marin
ANIMAL duck canard arlequin, harle huppe, sarcelle marbree, erismature
LANGUAGE language_pa espagnol, castillan, creole panameen, espagnol panameen
LANGUAGE language_kz russe, kazakh
LANGUAGE language_gh Ève, asante, adangme, akyem
LANGUAGE language_us navajo, nomlaki, tubatulabal, gros-ventre
LANGUAGE language_ch francais, italien, allemand, romanche
LANGUAGE language_ee anglais, russe, ukrainien, estonien
LANGUAGE language_ve espagnol
LANGUAGE language_st portugais, principense, saotomense
LANGUAGE language_tj tadjik, russe
LANGUAGE language_gm anglais, wolof, peul, soninke
LANGUAGE language_it sassarais, mochene, venitien, triorasque
LANGUAGE synonym_of_language langue de la passion, langue de eminescu, langue de shakespeare, langue de hemingway
LANGUAGE language_ws samoan, anglais
LANGUAGE language_cl espagnol, kunza, kawesqar, mapuche
LANGUAGE language_zw tonga, ndau, nambya, xhosa
LANGUAGE constructed_language novlangue, zorglangue, kriollatino, syldave
LANGUAGE language_ru bachkir, adygueen, tchouvache, evene
LANGUAGE language_sd banda-ndele, nobiin, four, arabe
LANGUAGE language_my malaisien, hakka, malais kedah, minnan
LANGUAGE language_va italien, latin, francais
LANGUAGE language_bo takana, moseten, besiro, machineri
LANGUAGE language_zm lozi, tonga, bemba, anglais
LANGUAGE language_mg malgache, francais
LANGUAGE language_lk cingalais, tamoul, anglais
LANGUAGE language_cv portugais
LANGUAGE language_tl tetoum, portugais, makasai, mambai
LANGUAGE language_ma tarifit, tachelhit, tamazight, darija
LANGUAGE language_ug gungu, amba, bari, masaba
LANGUAGE language_dk danois
LANGUAGE language_af moghol, domari, ouzbek
LANGUAGE language_lt lituanien, russe
LANGUAGE language_no finnois, kvene, same du sud, norvegien
LANGUAGE language_np nepalais, maithili
LANGUAGE language_na ndonga, wambo, khoikhoi, nama
LANGUAGE language_sr surinamais, neerlandais
LANGUAGE language kvene, akposso, yuracare, siraya
LANGUAGE language_bj yoruba, guin, yorouba, bariba
LANGUAGE language_sy arabe, arabe levantin septentrional
LANGUAGE language_ye arabe
LANGUAGE language_lb arabe
LANGUAGE language_ne tamasheq, songhai, kanouri, fulfulde
LANGUAGE language_sc creole seychellois, l'anglais, francais
LANGUAGE language_ec zaparo, quechua, espagnol, shuar
LANGUAGE language_in telougou, gujarati, kashmiri, malayalam
LANGUAGE language_be neerlandais, champenois, francais, gaumais
LANGUAGE language_gt jacalteco, achi, chuj, quiche
LANGUAGE language_lu luxembourgeois, francais, allemand
LANGUAGE language_tv anglais, tuvaluan
LANGUAGE language_bz espagnol, mopan, q’eqchi’, garifuna
LANGUAGE language_et sidama, tigrinya, oromo, omali
LANGUAGE language_br wayampi, kinikinao, wanano, guana
LANGUAGE language_ke swahili, luyia, gusii, luo
LANGUAGE language_do espagnol, creole haitien
LANGUAGE language_cg swahili, kikongo, francais, lingala
LANGUAGE language_ca tlingit, slavey, heiltsuk, anglais
LANGUAGE language_qa arabe
LANGUAGE language_fr alsacien, chtis, catalan, corse
LANGUAGE language_tn darija, francais, chelha, arabe
LANGUAGE language_mw nyanja, tonga, nyakyusa, nkhonde
LANGUAGE language_ro roumain
LANGUAGE language_so somali, arabe, oromo, borana
LANGUAGE language_nc paici, nengone, drubea, iaai
LANGUAGE dead_language nomlaki, atsahuaca, gaulois, aka-bea
LANGUAGE language_cr espagnol, mangue
LANGUAGE language_ge armenien, russe, azeri, georgien
LANGUAGE language_se suedois
LANGUAGE language_co piapoco, palenquero, quechua de napo, cumanagoto
LANGUAGE language_bf marka, peul, phuie, dioula
LANGUAGE language_ar nivacle, chana, quechua, toba
LANGUAGE language_hn pech, miskito, lenca, espagnol
LANGUAGE language_ng tiv, edo, igbo, yorouba
LANGUAGE language_ua russe, ukrainien
LANGUAGE language_gq yasa, bubi, kwasio, espagnol
LANGUAGE language_th lahu, iu mien, thai, khmer
LANGUAGE language_pe quechua, andoke, secoya, espagnol
LANGUAGE language_mm mon, shan, rohingya, birman
LANGUAGE language_gw peul, balante, portugais, sarakole
LANGUAGE language_ly nafusi, arabe, zouara
LANGUAGE language_sl anglais, loko, bom, kissi du nord
LANGUAGE language_au anglais, uradhi, anguthimri, awabakal
LANGUAGE language_kg russe, kirghize, ouzbek
LANGUAGE language_md roumain, bulgare, russe, ukrainien
LANGUAGE language_me serbe, bosnien, montenegrin, croate
LANGUAGE language_za venda, swazi, xhosa, zoulou
LANGUAGE language_sg tamil, malaisien, mandarin, malais
LANGUAGE language_nl frysk, frison occidental, bas allemand, romani
LANGUAGE Langues morte amanaye, vieux-nordique, vieil islandais, alsea
LANGUAGE language_tg mina, mobaa, kabiye, francais
LANGUAGE language_ao portugais
LANGUAGE language_de allemand, haut allemand, sorabe, francique mosellan
LANGUAGE language_py espagnol, guarani
LANGUAGE language_mo portugais
LANGUAGE language_ml foulfoulde, bambara, kassonke, maraka
LANGUAGE language_nr nauruan, anglais
LANGUAGE language_eh chleuh, darija, arabe, hassanya
LANGUAGE language_fi finnois, suedois, same du nord, carelien
LANGUAGE language_sk hongrois, slovaque
LANGUAGE language_es occitan, catalan, espagnol, galicien
LANGUAGE language_rw swahili, francais, anglais, kinyarwanda
LANGUAGE language_pt portugais
LANGUAGE language_gn toma, soussou, malinke, guerze
LANGUAGE language_ph surigaonon, tagalog-filipino, tausug, waray-waray
LANGUAGE language_om anglais, arabe, omanais
LANGUAGE language_pg anglais, tok pisin, hiri motou
LANGUAGE language_hr croate, hongrois
LANGUAGE language_lv russe, letton
LANGUAGE language_al albanais
LANGUAGE language_by ukrainien, bielorusse
LANGUAGE language_sn peul, wolof, bambara, saafi
LANGUAGE language_la lao
LANGUAGE language_gb anglais
LANGUAGE language_mr imraguen, wolof, malinke de le ouest, arabe
LANGUAGE language_hu hongrois
LANGUAGE language_gf palikur, mataray, kali'na, wayampi
LANGUAGE language_bi kirundi, kiswahili
LANGUAGE language_mz portugais, swati, chopi, nyungwe
LANGUAGE language_ba croate
LANGUAGE language_cz tcheque
LANGUAGE language_tw taiwanais, holo, hoklo, hakka
LANGUAGE language_tm turkmene, russe
LANGUAGE language_pr espagnol
LANGUAGE language_vn bouyei, laha, viet, tay
LANGUAGE language_ls swati, anglais, zoulou, sotho
LANGUAGE language_uz ouzbek, tadjik, russe, tadjike
LANGUAGE language_mx otomi de queretaro, jacalteque, zapoteque, huaxteque
LANGUAGE language_id manggarai, bima, sasak, aceh
LANGUAGE language_ci dioula, malinke, abron, agni
LANGUAGE language_nz maori, anglais
LANGUAGE language_tr azeri, zazaki, turc, arabe
LANGUAGE language_mn bouriate, mongol khalkha, mongol, oirate
LANGUAGE language_tt creole, anglais
LANGUAGE language_jp japonais, ainou, okinawaien
LANGUAGE language_ss toposa, anglais, nuer-dinka, arabe
LANGUAGE language_az boudoukh, budukh, rutul
LANGUAGE language_ga bubi, francais, baka, duma
LANGUAGE language_kr coreen
LANGUAGE language_fm mwoakiloa, carolinien, paafang, mokil
LANGUAGE language_tk tokelau, anglais, tokelauan
LANGUAGE language_lr bassa, gola, mano, vai
LANGUAGE language_vu bichelamar, tanna du nord, aoba, paama
LANGUAGE language_at allemand, walser, hongrois, slovene
LANGUAGE language_pl polonais
LANGUAGE language_pk anglais, pachto, pendjabi, ourdou
LANGUAGE language_eg domari, siwi, arabe saʿidi, arabe egyptien
LANGUAGE language_cn zhuang de yongnan, zhuang de guibei, zhuang de yongbei, chinois
LANGUAGE language_sz anglais, swati
LANGUAGE language_nu vagahau niue, tafiti, niueen, motu
LANGUAGE language_tz anglais, sukuma, kiswahili, gogo
LANGUAGE language_rs serbe
LANGUAGE language_ni espagnol
LANGUAGE language_kp coreen
LANGUAGE language_cm makari, francais, ewondo, awing
LANGUAGE language_er tigrigna, tigre, bilen, bedja
OBJECT music_instrument mirliton, akonting, autoharpe, pianocktail
OBJECT underwear string, dampmart, camisole, corset
OBJECT hat kokochnik, chapel, kebour, mirliton
OBJECT machine essuyeur, decapeuse, radio, scanner
OBJECT medicine nematicide, p-acetylaminophenol, medicament, ivermectine
OBJECT clothing manche de lustrine, surcot, pantalon a pont, dhoti
OBJECT shoes talon aiguille, charentaise, cuissarde, richelieu
OBJECT measuring_instrument decimetre, secohmmetre, ophtalmometre, palmer
OBJECT tool tronconneuse, cle lavabo, drill, poincon
OBJECT kitchenware ramequin, cuillere en bois, cuillere a sauce, casse-noix
OBJECT appliance congelateur, nettoyeur a vapeur, lave-linge, singer
OBJECT armor soleret, armet, kabuto, ocrea
OBJECT firearm falo, fusil-mitrailleur, mortier, escopette
OBJECT furniture table a langer, banquette, ambon, fauteuil
OBJECT bladed_weapon latte, couteau suisse, douk-douk, ninjato
TIME time_lapse bisannuel, annuel, seculaire, mensuel
TIME month juill., aout, 9bre, xbre
TIME timespace aujourd'hui, veille, matin, soir
TIME weekday lun., lundi, mar., mercredi
TIME season saison humide, hiver, printemps, ete
VEHICULE boat galvette, pirogue, foncet, hors-bord
VEHICULE vehicule vehicule spatial, hydravion, ratrak, tandem
VEHICULE car mazda, berline, quatre-chevaux, taxi
VEHICULE aircraft adav, sesquiplan, b-52, ulm
LOCATION country norfolk, sint maarten, fidji, belize
LOCATION state_mexico yucatan, morelos, guanajuato, basse-californie
LOCATION state_brazil mato grosso do sul, tocantins, bahia, minas gerais
LOCATION state_south_sudan jonglei, unite, equatoria-oriental, equatoria-occidental
LOCATION cardinal_point ouest-quart-sud-ouest, sud-sud-ouest-demi-sud, sud-ouest demi-ouest, sud demi-ouest
LOCATION religious_building collegiale, stupa, oratoire, tumulus
LOCATION building_restauration glacier, resto-brasserie, camion pizza, pub-restaurant
LOCATION shop salon de coiffure, boite de nuit, pharmacie, tele-boutique
LOCATION factory cimenterie, ferronnerie, usine, limonaderie
LOCATION state_australia australie-meridionale, queensland, tasmanie, australie-occidentale
LOCATION city cogna, bainville-aux-saules, tlokweng, saint-francois-de-sales
LOCATION room cuisine, balcons, grenier, cave
LOCATION volcano grimsvotn, piton de la fournaise, grimsvoetn, etna
LOCATION planet pegaside, epimethee, jupiter chaud, galatee
LOCATION state_sudan darfour-central, al djazirah, sannar, khartoum
LOCATION mountain mont aigoual, cantabriques, monts des geants, charmant som
LOCATION continent ancien monde, amerique du nord, hindoustan, oceanie
LOCATION administrative_district etat, wilaya, comitat, subdivision
LOCATION alternative_country_name pays des kangourous, pays du fromage, pays du cedre, pays des aigles
LOCATION strait detroit de sele, detroit de balabac, bosphore, detroit de cook
LOCATION sub-prefecture sedan, charolles, chateau-chinon ( ville ), cherbourg-octeville
LOCATION peninsula alaska, crimee, floride, black isle
LOCATION ocean mer des indes, atlantique sud, ocean atlantique nord, ocean arctique
LOCATION sea mer ionienne, mer de azov, mediterranee asiatique, mediterranee americaine
LOCATION dessert aralkum, atacama, kyzylkoum, desert du cholistan
LOCATION golf/bay golfe persique, golfe de biafra, baie de fundy, golfe de bohai
LOCATION prefecture quimper, besancon, lille, troyes
LOCATION building hospice, kiosque, prison, tombe
LOCATION state_india chattisgarh, mizoram, rajasthan, karnataka
LOCATION state_burma rakhine, kayin, mon, shan
LOCATION river ijssel, belles-dames, mobile, lwalaba
LOCATION lake amqui, buscaylet, euripe, lac caspien
LOCATION state_usa delaware, maine, caroline du nord, colorado
OTHER molluscicide mercaptodimethur, metaldehyde, methiocarbe, methomyl
OTHER alkaloid anagyrine, aniline, arborescidine, atropine
OTHER metal metal, actinium, alu, aluminium
OTHER fungicide 8-hydroxyquinoleine, acibenzolar-s-methyle, acide ascorbique, ammonium quaternaire
OTHER science actinologie, aeraulique, aeropalynologie, agnotologie
OTHER pesticide acaricide, corvifuge, fongicide, herbicide
OTHER musical_genre acid jazz, bel canto, blackdoom, black metal
OTHER news actualite, fait divers
OTHER game action ou verite, airsoft, babyfoot, baguenaudier
OTHER document reglement, reglement de copropriete, reglement interieur, reporting
OTHER nematicide 1,2-dichloropropane, 1,3-dichloropropene, abamectin, aldicarbe
OTHER peculiar_informal_demonym americain, arabe du coin, armee mexicaine, auberge espagnole
OTHER rodenticide aceto-arsenite de cuivre, alpha naphtyl indane dione, alphachloralose, ancymidole
OTHER mineral aakerite, aarite, abkhazite, abrazite
OTHER currency cent, centime, centime d’euro, eurocent
OTHER insecticide phosphure d’aluminium, phosphure de magnesium, phoxime, pirimicarbe
OTHER respect affection, civilite, estime, tolerance
OTHER ordinal 1er, 10e, 100e, 1000e
OTHER orphan_disease maladie orpheline, coxa-retrorsa, coxa vara, epiphysiolyse des adolescents
OTHER horse_color alezan, aquilain, arzel, aubere
OTHER acaricide abamectin, acrinathrine, amitraze, avermectin b1a
OTHER card_game 8 americain, aluette, ascenseur, baccara
OTHER illness/virus virus, adenovirus, arbovirus, coronavirus
OTHER network_protocol adsl, anneau a jeton, arp, ascii
OTHER combat_sport sport de combat, boxe, boxe anglaise, escrime
OTHER fear peur, anxiete, couardise, trouble
OTHER chemical_substance acetal, acetate, 4-acetylaminophenol, p-acetylaminophenol
OTHER collection abecedephilie, absinthiophilie, aerophilatelie, akkordiophilie
OTHER phobic acoustophobe, aerodromphobe, aerophobe, agoraphobe
OTHER human_body_muscle abdominal, abdominaux, abducteur, adducteur
OTHER plant_growth acide 2,4-dichlorophenoxyacetique, acide 4-chloro-phenoxyacetique, acide alpha naphtylacetique, acide chloro-4-phenoxyacetique
OTHER animal_sound zinzibulement, zinzibuler, zinzinulement, zinzinuler
OTHER disgust degout, amertume, depit, repugnance
OTHER hominid australopitheque, denisovien, etre humain, gigantopitheque
OTHER anatomy tete, visage, front, oreille
OTHER chemical_element unhexunium, unnilbium, unnilennium, unnilhexium
OTHER herbicide metobromuron, metolachlor, metolachlore, metoprotryne
OTHER skin_illness acne, couperose, eczema, erytheme
OTHER electrical_component allume-cigare, ballast, biorupteur, bobine
OTHER phobia lalophobie, lathophobie, lesbophobie, leukophobie
OTHER feeling affection, emotion, sentiment, passion
OTHER crime_or_misdeameanor abus de biens sociaux, abus de confiance, abus de faiblesse, arnaque
OTHER psychiatric_illness demonomanie, demonopathie, paranoia, schizophrenie
OTHER company airbus, google, intel, apple
OTHER mail courrier, messagerie, missive, expedition
OTHER happiness bonheur, felicite, paix, ravissement
OTHER setellite s/2000 j 10, s/2000 j 2, s/2000 j 3, s/2000 j 4
OTHER electronic_component composant electronique, bigrille, bobine, chipset
OTHER misfortune malheur, desastre, chagrin, fleau
OTHER illness tuberculose, tularemie, tumeur, tumeur melanique
OTHER trouble_language alalie, alogie, anarthrie, aphasie
OTHER rock ardoise, ardoisine, arenite, arkose
OTHER maritime_route canal, chenal, detroit, goulet
OTHER computer_language langage de programmation, ada, algol, algol w
OTHER bactericide acide ethane-carboxylique, acide propanoique, acide propionique, ammonium quaternaire
OTHER drinking_game jeu a boire, barathon, biere-pong, caps
OTHER eye_illness achromatopsie, amaurose, ambliopie, amblyope
OTHER wind vent, agueil, alize, aquilon
OTHER delight plaisir, bein-etre, complaisance, delice
OTHER award cesar, croix de victoria, gerard, goncourt
OTHER bacteria bacterie, acetobacter, achromobacter, actinobacterie
OTHER psychotropic_drug psychotrope, alcool ethylique, cafe, carbonate de lithium
OTHER imagination imagination, chimere, creation, invention
OTHER martial_art art martial, aikido, boxe chinoise, boxe thailandaise
OTHER amino_acid acide amine, acide glutamique, alanine, arginine
OTHER human_body_bone acetabulum, arete, astragale, atlas
OTHER derived_from_illness alcoolique, anorexique, anticoquelucheux, antisyphilitique
OTHER weather neige, pluie, orage, tonnerre
OTHER despair chagrin, desespoir, accablement, brisement
OTHER dance danse, alexandrine, allemande, anglaise
OTHER constellation aigle, andromede, antinous, argo
OTHER suffering souffrance, blessure, affliction, torture
OTHER color couleur, blanc, azur, bleu
OTHER fatty_acid acide amylique, acide arachidique, acide behenique, acide butanoique
OTHER organization velo v, kalachuri, union astronomique internationale, iota sigma pi
OTHER success succes, celebrite, fortune, prouesse
OTHER drug drogue, acide, aya, ayahuasca
OTHER alloy alliage, 45 permalloy, acier, acier inoxydable
OTHER geological_time aalenien, acadien, acheuleen, aeronien
OTHER corvid_repellent corvifuge, alphachloralose, anthraquinone, chloralose
OTHER enallage balnave, bedave, bicrave, bouillave
OTHER sexual_position position sexuelle, 69, 99, andromaque
OTHER unit_of_measure zeptosteradian, zeptotesla, zeptovolt, zeptowatt
OTHER sliding_sport sport de glisse, barefoot, boardercross, bobsleigh
OTHER figure_of_speech figure de rhetorique, figure de style, figure rhetorique, abregement
OTHER social_class etudiant, riche, pauvre, patron
OTHER traffic_lane boulevard peripherique, peripherique exterieur, peripherique interieur, route
OTHER enzyme adn polymerase, alpha-amylase, amylase, arn polymerase
OTHER fuel carburant, agrocarburant, bio-ethanol, biocarburant
OTHER sport twirling baton, ultimate, ultra-marathon, ultrafond
OTHER event imprevu, evenement, actualite, date
OTHER Sport combat sport de combat, boxe, boxe anglaise, dambe
OTHER textile abaca, acetate, adatis, alexandrine
OTHER issue probleme, problematique, difficulte, souci
OTHER zodiac_sign balance, belier, cancer, capricorne
OTHER religion asatru, bouddhisme, candomble, caodaisme
OTHER unkindness mechancete, agressivite, bassesse, desobligeance
OTHER toy jouet, ballon de baudruche, bilboquet, bille
OTHER attribute age, taille, poids, corpulence
OTHER std blennorragie, chancre mou, chlamydiose, gonorrhee
OTHER friendship amitie, accointance, camaraderie, attachement
OTHER organ larynx, glande salivaire, glandes salivaires, meninges
OTHER subatomic_particle antielectron, antilepton, antimuon, antineutrino

Adjective categories

If the adjective refers to a noun, the category of the adjective becomes that of the noun.

Adjective categories group up words that evocate a common concept, and gives them positive or negative values according to their intensities (when possible).

For instance, the category Difficulty includes the word facile with an intensity of 7.0, and the word difficile with an intensity of -7.0.

SUPER SUB VALUE RANGE EXAMPLES
- Anterior None avant
- Posterieur None apres
- Difficulty [-10, 10] facile, difficile, aisé
- Judgement [-10, 10] bon, mauvais
- Speed [-10, 10] lent, rapide
- Temporality None actuel
- Time None long, court
- Quantity None gros
- Scale [-10, 10] petit, grand
- Shape None carré, rond
- Beauty [-10, 10] moche, beau
- Color None jaune, bleu
- Happiness [-10, 10] content, malheureux
- Feelings None soucieux
- Trait None méchant, gentil, riche

Adverb categories

If the category of the adverb is 'manner' or 'time and aspect', then it takes the category of the adjective of reference.

SUPER SUB EXAMPLES
- manner ...
- quantity .....
- time and aspect ....
- location ....
- affirmation or doubt ....
- negation ....

Interjection categories

SUPER SUB EXAMPLES
- laught ...
- compliment .....
- thanks ....
- no ....
- yes ....
- goodbye ....
- greetings ....

Preposition categories

see Preposition sens and Preposition next

SUPER SUB EXAMPLES
- Approximation .....
- Comparaison .....
- Duration .....
Localisation Source ...
Localisation Destination .....
Localisation Origin .....
Localisation Passage .....
Localisation Position .....
Localisation Spatial Approximation .....
Localisation Temporal Approximation .....
Localisation Temporal Localisation .....
Localisation Interval Specification .....
- Manner .....
Manner Means .....
Manner Imitation .....
- Accompaniment .....
Accompaniment Addition .....
Accompaniment Concordance of Circumstance .....
Accompaniment Inclusion .....
Accompaniment Exclusion .....
- Quantity .....
Quantity Precise .....
Quantity Approximative .....
Quantity Frequency .....
Quantity Proportion .....
- Choices and exchanges .....
Choices and exchanges Exchange .....
Choices and exchanges Alternatives .....
Choices and exchanges Substitution .....
- Causality .....
Causality Intention .....
Causality Cause .....
- Opposition .....
Opposition Inverse .....
Opposition Position From .....
- Without Considering .....
- Gradation .....
Gradation Priority .....
Gradation Subordination .....
Gradation Hierarchy .....
Gradation Ranking .....
Gradation Degree Of .....
- Relation .....
- Theme .....

Preposition sens

see Preposition categories and Preposition next

CATEGORY EXAMPLES
TO ...
UNTIL .....
TOWARDS ....
PER ....
WITH ....
ON ....
AGAINST .....
WITHIN ....
FOR ....
ACCORDING_TO ....
FOLOWING ....
AT .....
BEYOND ....
OVER ....
UNDER ....
UP TO ....
AWAY FROM .....
NEAR ....
AROUND ....
ALONG ....
THROUGH ....
VIA .....
VIA FRONT ....
VIA BACK ....
VIA UNDER ....
VIA ABOVE ....
VIA EST .....
VIA WEST ....
VIA NORTH ....
VIA SOUTH ....
VIA TOP ....
VIA BOTTOM .....
VIA LEFT ....
VIA RIGHT ....
AT BEGINNING_OF ....
NEXT_TO ....
RIGHT_TO .....
LEFT_TO ....
FRONT_TO ....
BACK_TO ....
WEST_TO ....
EST_TO .....
INSIDE_TO ....
OUTSIDE_TO ....
CLOSE_TO ....
AFTER ....
AT END_OF .....
AT BOTTOM_OF ....
AT MIDDLE_OF ....
AT NORTH_OF ....
AT SOUTH_OF ....
OUTSIDE_OF .....
INSIDE_OF ....
BEYOND_OF ....
NORTH_OF ....
SOUTH_OF ....
AROUND_OF .....
ABOVE ....
BEFORE ....
IN ....
BEHIND ....
FRONT .....
NEARBY ....
AT FRONT ....
AT BACK ....
AT BOTTOM ....
AT TOP .....
OUTSIDE ....
FRONT_OF ....
OUT_OF ....
BETWEEN ....
RELATIVE_TO .....
FROM ....
FROM BACK ....
FROM FRONT ....
FROM UNDER ....
FROM ABOVE ....
FROM EST ....
FROM WEST ....
FROM NORTH ....
FROM SOUTH ....
FROM INSIDE ....
FROM OUTSIDE ....
NULL ....

Preposition next

see Preposition sens and Preposition next

NEXT EXAMPLE
space
time
abstract
matter
situation
NULL

Changelogs

15/10/20

7/11/19

25/04/19

15/04/19

25/03/19

19/03/19

13/03/19

27/02/19

13/02/19

05/02/19