Loading [a11y]/accessibility-menu.js
A bi-directional LSTM approach for polyphone disambiguation in Mandarin Chinese | IEEE Conference Publication | IEEE Xplore

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


Abstract:

Polyphone disambiguation in Mandarin Chinese aims to pick up the correct pronunciation from several candidates for a polyphonic character. It serves as an essential compo...Show More

Abstract:

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.
Date of Conference: 17-20 October 2016
Date Added to IEEE Xplore: 04 May 2017
ISBN Information:
Conference Location: Tianjin, China

References

References is not available for this document.