Pronunciation-enhanced Chinese word embedding

Qinjuan YANG, Haoran XIE, Kwok Shing CHENG, Fu Lee WANG, Yanghui RAO

Research output: Contribution to journalArticlespeer-review


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. Copyright © 2021 The Author(s).
Original languageEnglish
JournalCognitive Computation
Early online date22 Feb 2021
Publication statusE-pub ahead of print - 22 Feb 2021


Yang, Q., Xie, H., Cheng, G., Wang, F. L., & Rao, Y. (2021). Pronunciation-enhanced Chinese word embedding. Cognitive Computation. Advance online publication. doi: 10.1007/s12559-021-09850-9


  • Chinese embedding
  • Pronunciation
  • Chinese characters
  • Sentiment analysis

Fingerprint Dive into the research topics of 'Pronunciation-enhanced Chinese word embedding'. Together they form a unique fingerprint.