Adversarial Multi-Criteria Learning for Chinese Word Segmentation

TL;DR

This paper introduces an adversarial multi-criteria learning approach for Chinese word segmentation that leverages multiple segmentation standards to improve overall performance across diverse datasets.

Contribution

It proposes a novel adversarial learning framework that integrates shared knowledge from heterogeneous segmentation criteria for Chinese word segmentation.

Findings

Significant performance improvements on eight different corpora.

Effective exploitation of multiple criteria enhances segmentation accuracy.

Source code is publicly available on Github.

Abstract

Different linguistic perspectives causes many diverse segmentation criteria for Chinese word segmentation (CWS). Most existing methods focus on improve the performance for each single criterion. However, it is interesting to exploit these different criteria and mining their common underlying knowledge. In this paper, we propose adversarial multi-criteria learning for CWS by integrating shared knowledge from multiple heterogeneous segmentation criteria. Experiments on eight corpora with heterogeneous segmentation criteria show that the performance of each corpus obtains a significant improvement, compared to single-criterion learning. Source codes of this paper are available on Github.