Learning Chinese Word Embeddings With Words and Subcharacter N-Grams
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Access"
DOI: 10.1109/access.2019.2908014
Abstract: Co-occurrence information between words is the basis of training word embeddings; besides, Chinese characters are composed of subcharacters, words made up by the same characters or subcharacters usually have similar semantics, but this internal substructure… read more here.
Keywords: chinese word; learning chinese; word embeddings; subcharacter grams ... See more keywords