TY - JOUR
T1 - Pronunciation-Enhanced Chinese Word Embedding
AU - Yang, Qinjuan
AU - Xie, Haoran
AU - Cheng, Gary
AU - Wang, Fu Lee
AU - Rao, Yanghui
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/5
Y1 - 2021/5
N2 - Chinese word embeddings have recently garnered considerable attention. Chinese characters and their sub-character components, which contain rich semantic information, are incorporated to learn Chinese word embeddings. Chinese characters can represent a combination of meaning, structure, and pronunciation. However, existing embedding learning methods focus on the structure and meaning of Chinese characters. In this study, we aim to develop an embedding learning method that can make complete use of the information represented by Chinese characters, including phonology, morphology, and semantics. Specifically, we propose a pronunciation-enhanced Chinese word embedding learning method, where the pronunciations of context characters and target characters are simultaneously encoded into the embeddings. Evaluation of word similarity, word analogy reasoning, text classification, and sentiment analysis validate the effectiveness of our proposed method.
AB - Chinese word embeddings have recently garnered considerable attention. Chinese characters and their sub-character components, which contain rich semantic information, are incorporated to learn Chinese word embeddings. Chinese characters can represent a combination of meaning, structure, and pronunciation. However, existing embedding learning methods focus on the structure and meaning of Chinese characters. In this study, we aim to develop an embedding learning method that can make complete use of the information represented by Chinese characters, including phonology, morphology, and semantics. Specifically, we propose a pronunciation-enhanced Chinese word embedding learning method, where the pronunciations of context characters and target characters are simultaneously encoded into the embeddings. Evaluation of word similarity, word analogy reasoning, text classification, and sentiment analysis validate the effectiveness of our proposed method.
KW - Chinese characters
KW - Chinese embedding
KW - Pronunciation
KW - Sentiment analysis
UR - http://www.scopus.com/inward/record.url?scp=85101552516&partnerID=8YFLogxK
U2 - 10.1007/s12559-021-09850-9
DO - 10.1007/s12559-021-09850-9
M3 - Article
AN - SCOPUS:85101552516
SN - 1866-9956
VL - 13
SP - 688
EP - 697
JO - Cognitive Computation
JF - Cognitive Computation
IS - 3
ER -