granawkins / latent-dictionary

A dictionary, but it shows you position in embedding space relative to some synonyms/antonyms instead of a definition.
MIT License
69 stars 7 forks source link

Get word lists in 10 languages from nltk #14

Open granawkins opened 1 month ago

granawkins commented 1 month ago

During the startup sequence, use nltk to get the most common 10,000 words in 10 languages. You may need to add it as a dependency. For now just save them in a dir, e.g. 'wordlist/english.txt'.

granawkins commented 1 month ago

@mentatbot can you do this?

mentatbot[bot] commented 1 month ago

I will start working on this issue