Sentence
Introduction
The Sentence level is the second level of output and provides analysis of individual sentences within the text. The Sentence Object contains subtypes such as Tokens, Sub Sentences, Coreference, Emotion, and Patterns.
The Tokens subtype breaks down the sentence into individual words and provides information about each one, while the Sub Sentences subtype identifies and groups together sub-sentences within the main sentence. The Coreference subtype identifies and groups together mentions of the same entity within the sentence, and the Emotion subtype detects and categorizes emotions expressed in the sentence. The Patterns subtype identifies common patterns or themes within the sentence.
Overall, the Sentence returned by the API offers a detailed analysis of each sentence within the text, providing insight into the meaning and structure of the sentence.
Format
Sentence are received inside an Array()
| Key | Type | Description |
|---|---|---|
source | String | Source of the document without normalisation |
sentence_indexes | [number, number] | Language of the document |
source_pure | String | Source of the document without normalisation |
detail | Token [ ] | Tokens |
subsentences | Subsentence [ ] | Sub sentences inside the document |
ml_ner | ML NER | Corefence inside the document |
ml_sentiment | ML sentiment | Corefence inside the document |
ml_emotion | ML emotion | Corefence inside the document |
coreference | number[] | Coreference Indexes |
sentiment | Sentiment | Sentences inside the document |
emotion | Emotion | Sentences inside the document |
sentence_type | String | All sentence types |