Skip to main content
Version: 2.0

Common Properties

Properties have 'upward' accessibility, properties at a lower level are accessible at a higher level:

NLP > Document > Sentence >= Subsentence > Token

For example 'str' which is a token property can be accessed at all analysis levels (NLP/Document/Sentence/Subsentence/Token)

Conversely, 'emotion_doc' is only available at the Document level, and at the NLP level which groups multiple documents

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

Document properties

NametypeDescription
str_docstringReturns the text of the whole document after tokenization
original_text_docListReturns the original text of the whole document
emotion_docStringReturns emotions detected on the whole document at once
sentiment_docStringReturns sentiments detected on the whole document at once
domain_docStringReturns classification by domain to allow loading certain dictionary / specific entities (Healthcare, Legal, Finance etc)
type_docStringReturns type of input (contract, article, tweet, reviews, conversation, etc)
emoticon_docEmoticon ObjectReturns global text emoticons
spansListReturns spans in the document
clustersListReturns cluster in the document

Sentence/Subsentence properties

NametypeDescription
strStringReturns sentence as a string
original_textStringReturns the original sentence in the input text before modification from the tokenization
tokensListReturns a list of Token Instances from the sentence
synthesisListReturns synthesis of sentence data
detaillistReturn list of sentence details
emotionTupleReturns emotion as tuple (Type, score)
emotion_mlListReturns emotion of ml_model without further fine tuning
sentimentDictionaryReturns sentiment with positive, negative and total values
sentiment_mlDictionaryReturns sentiment of ml_model without further fine tuning
sentence_typeStringReturns the type of sentence
languageStringReturns detected language
spansListReturns spans in the sentence
clustersListReturns clusters in the sentence

Token properties

NametypeDescription
strStringReturns string of token
sourceStringReturns string of token
original_textStringReturns the original token in the input text before modification from the tokenization
posStringReturns POS (Part-of-Speech)
nerNER ObjectReturns actual (combines NER & ML_NER)
lemmaStringReturns the lemma
lemma_detailListReturns details of lemmatizer
auxiliaryStringReturns unmerged lemma
genderStringReturns gender of token
pluralStringReturns whether token is singular or plural
infinitiveStringReturns infinitive of token if verb
modeStringReturns mode of token if verb
conjugateStringReturns conjugate of token if verb
morphologyStringReturns morphological features
depStringReturns dependency relations
refIntegerReturns the index of the parent dependence -1 for root, else >= 0
meaningListReturns meanings as tuples (SUPER, SUB)
spansListReturns spans that contain the token
clustersListReturns clusters that contain the token

For a demo of common properties check out our tutorial ๐Ÿ‘จ๐Ÿปโ€๐Ÿ’ป