Unsupervised Neural Word Segmentation for Chinese via Segmental Language Modeling

TL;DR

This paper introduces a novel neural segmental language model for unsupervised Chinese word segmentation, explicitly modeling segments and achieving competitive results with state-of-the-art statistical methods.

Contribution

It is the first to propose a neural model for unsupervised Chinese word segmentation that explicitly captures segmental structure.

Findings

Achieves competitive performance on four datasets from SIGHAN 2005.

First neural approach to unsupervised Chinese word segmentation.

Demonstrates the effectiveness of segmental language modeling.

Abstract

Previous traditional approaches to unsupervised Chinese word segmentation (CWS) can be roughly classified into discriminative and generative models. The former uses the carefully designed goodness measures for candidate segmentation, while the latter focuses on finding the optimal segmentation of the highest generative probability. However, while there exists a trivial way to extend the discriminative models into neural version by using neural language models, those of generative ones are non-trivial. In this paper, we propose the segmental language models (SLMs) for CWS. Our approach explicitly focuses on the segmental nature of Chinese, as well as preserves several properties of language models. In SLMs, a context encoder encodes the previous context and a segment decoder generates each segment incrementally. As far as we know, we are the first to propose a neural model for unsupervised CWS and achieve competitive performance to the state-of-the-art statistical models on four different datasets from SIGHAN 2005 bakeoff.