lexicons_builder documentation

The lexicons_builder package aims to provide a basic API to create lexicons related to specific words.

Key principle: Given the input words, the main algorithm will look for synonyms and neighboors in the synonym dictionaries, in the NLP model(s) provided and in WordNet. For each of the new retrieved terms, it will look again for its neighboors or synonyms and so on..

The general method is implemented on 3 different supports:

  1. Synonyms dictionaries (See complete list of the dictionaries here)

  2. NLP language models (Word2Vec or FastText format)

  3. WordNet (or WOLF)

Output can be text file, turtle file or a Graph object. See Quickstart section for examples.


The synonyms comming from the web are retreived by scrapping each webpage. Which means that a change in the html might return wrong results.


Indices and tables


If you encounter an issue, feel free raise it on GitHub