Phonetic-enriched Text Representation for Chinese Sentiment Analysis with Reinforcement Learning

TL;DR

This paper introduces a novel phonetic feature encoding and a reinforcement learning-based network to improve Chinese sentiment analysis by leveraging pronunciation and intonation, outperforming existing character-level methods.

Contribution

It proposes a new phonetic feature encoding and a reinforcement learning model to enhance Chinese sentiment analysis by incorporating pronunciation and intonation information.

Findings

Phonetic features significantly improve sentiment analysis accuracy.

The DISA network effectively disambiguates intonations for better representations.

The approach outperforms state-of-the-art Chinese character-level models.

Abstract

The Chinese pronunciation system offers two characteristics that distinguish it from other languages: deep phonemic orthography and intonation variations. We are the first to argue that these two important properties can play a major role in Chinese sentiment analysis. Particularly, we propose two effective features to encode phonetic information. Next, we develop a Disambiguate Intonation for Sentiment Analysis (DISA) network using a reinforcement network. It functions as disambiguating intonations for each Chinese character (pinyin). Thus, a precise phonetic representation of Chinese is learned. Furthermore, we also fuse phonetic features with textual and visual features in order to mimic the way humans read and understand Chinese text. Experimental results on five different Chinese sentiment analysis datasets show that the inclusion of phonetic features significantly and consistently improves the performance of textual and visual representations and outshines the state-of-the-art Chinese character level representations.