lute-v3
lute-v3 copied to clipboard
Add language: Modern Chinese
- Add modern chinese parser that can detect Chinese mutiple-character-words and some test cases.
- Add langauge config and the story.
By default using the pkuseg for parsing Chinese, if user want a more accurate parser, can install hanlp by pip.
Have created a PR for this
Seriously, it is not called “Modern Chinese”. Maybe you mean “Mandarin Chinese”. Other Chinese dialects have largely different vocabularies.
Seriously, it is not called “Modern Chinese”. Maybe you mean “Mandarin Chinese”. Other Chinese dialects have largely different vocabularies.
We already have 'Classical Chinese'. So, in that context, it's fair to say 'modern'. Probably best to not debate that stuff here. :)
Mandarin is added :-), old issue, closing.