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.
Bibliographical noteThis research was supported by Research Grants Council of Hong Kong SAR, China (UGC/FDS16/E01/19), General Research Fund (No. 18601118) of Research Grants Council of Hong Kong SAR, China, One-of Special Fund from Central and Faculty Fund in Support of Research from 2019/20 to 2021/22 (MIT02/19- 20) of The Education University of Hong Kong, Hong Kong, HKIBS Research Seed Fund 2019/20 (190-009), the Research Seed Fund (102367), and LEO Dr David P. Chan Institute of Data Science of Lingnan University, Hong Kong. We are grateful to Xiaorui Qin for her work on sentiment analysis experiments.
- Chinese characters
- Chinese embedding
- Sentiment analysis