A bi-directional LSTM approach for polyphone disambiguation in Mandarin Chinese

Changhao Shan, Lei Xie, Kaisheng Yao

科研成果: 书/报告/会议事项章节会议稿件同行评审

23 引用 (Scopus)

摘要

Polyphone disambiguation in Mandarin Chinese aims to pick up the correct pronunciation from several candidates for a polyphonic character. It serves as an essential component in human language technologies such as text-to-speech synthesis. Since the pronunciation for most polyphonic characters can be easily decided from their contexts in the text, in this paper, we address the polyphone disambiguation problem as a sequential labeling task. Specifically, we propose to use bidirectional long short-term memory (BLSTM) neural network to encode both the past and future observations on the character sequence as its inputs and predict the pronunciations. We also empirically study the impacts of (1) modeling different length of contexts, (2) the number of BLSTM layers and (3) the granularity of part-o-speech (POS) tags as features. Our results show that using a deep BLSTM is able to achieve state-of-the-art performance in polyphone disambiguation.

源语言英语
主期刊名Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016
编辑Hsin-Min Wang, Qingzhi Hou, Yuan Wei, Tan Lee, Jianguo Wei, Lei Xie, Hui Feng, Jianwu Dang, Jianwu Dang
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9781509042937
DOI
出版状态已出版 - 2 5月 2017
活动10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016 - Tianjin, 中国
期限: 17 10月 201620 10月 2016

出版系列

姓名Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016

会议

会议10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016
国家/地区中国
Tianjin
时期17/10/1620/10/16

指纹

探究 'A bi-directional LSTM approach for polyphone disambiguation in Mandarin Chinese' 的科研主题。它们共同构成独一无二的指纹。

引用此