Skip to content



The Token level is the third level of output and provides analysis of individual words within a sentence. The Token Object contains subtypes such as Meaning and Lemmatizer.

The Meaning subtype provides information about the definition and context of the word, while the Lemmatizer subtype identifies the base form of the word.

Overall, the Token returned by the API offers a detailed analysis of each word within a sentence, providing insight into the meaning and context of the word.


Tokens are received inside an Array()

sourceStringSource of the document without normalisation
tagStringList of all tags
source_pureStringSource of the document without normalisation
indexes[number, number]Indexes of the token in the source
lemmaStringLemma of the token
lemmatizerLemmatizerLemmatizer of the token
meaningMeaningList of all meanings
valueobjectValue of the token
lenNumberLength of the token
depStringList of all dependencies
refNumberReference of the token
indexNumberIndex of the token
coreferencenumber []Coreference of the token

Next steps