Chinese Word Segmentation with Heterogeneous Graph Neural Network

TL;DR

This paper introduces HGNSeg, a novel framework combining pre-trained language models and heterogeneous graph neural networks to enhance Chinese word segmentation by effectively integrating multi-level linguistic information and structural features.

Contribution

The paper presents a new approach that leverages heterogeneous graph neural networks with external linguistic information, addressing integration and structural feature challenges in CWS.

Findings

Improves segmentation accuracy on six benchmark datasets.

Effectively alleviates out-of-vocabulary issues in cross-domain scenarios.

Demonstrates strong performance compared to existing methods.

Abstract

In recent years, deep learning has achieved significant success in the Chinese word segmentation (CWS) task. Most of these methods improve the performance of CWS by leveraging external information, e.g., words, sub-words, syntax. However, existing approaches fail to effectively integrate the multi-level linguistic information and also ignore the structural feature of the external information. Therefore, in this paper, we proposed a framework to improve CWS, named HGNSeg. It exploits multi-level external information sufficiently with the pre-trained language model and heterogeneous graph neural network. The experimental results on six benchmark datasets (e.g., Bakeoff 2005, Bakeoff 2008) validate that our approach can effectively improve the performance of Chinese word segmentation. Importantly, in cross-domain scenarios, our method also shows a strong ability to alleviate the out-of-vocabulary (OOV) problem.