word2vecelastic - v1.0.0

Features

• Train word models based on an Elasticsearch index name
• Use Spacy to tokenize texts and detect hyphenated words which should not be split, e.g., "neo-liberalism"

Full Changelog: https://github.com/UUDigitalHumanitieslab/Word2VecElastic/commits/v1.0.0

- Python
Published by BeritJanssen over 2 years ago