bst-mug / acres

Acronym expansion module based on word embeddings and filtering rules
Apache License 2.0
1 stars 2 forks source link

Use 0 as digit marker #51

Open michelole opened 6 years ago

michelole commented 6 years ago

A digit marker should be on the same regex class of digits, so use any digit instead of Ð.

Relates to #17.

michelole commented 5 years ago

This also reduce memory consumption by not requiring Unicode (but we still need to transliterate ß).