search

vncorenlp / VnCoreNLP

A Vietnamese natural language processing toolkit (NAACL 2018)
Other
587 stars 145 forks source link

Add new word to VnCoreNLP #44

Closed ngovanminh3232 closed 1 year ago

ngovanminh3232 commented 1 year ago

I want to add new word to tokenizer Example: FIS Bank -> FIS_Bank Are you show me train VnCoreNLP? Thank you

datquocnguyen commented 1 year ago

You can add that word into the Vocabulary.java file: either COUNTRY_L_NAME.add("fis bank"); or VN_LOCATIONS.add("fis bank");, then recompile the whole toolkit via terminal by using: mvn clean install.