Unsupervised Neural Word Segmentation for Chinese via Segmental Language Modeling
This addresses the problem of segmenting Chinese text without labeled data for NLP applications, representing an incremental advance by introducing a neural approach to a previously statistical-dominated area.
The paper tackles unsupervised Chinese word segmentation by proposing segmental language models, achieving competitive performance with state-of-the-art statistical models on four SIGHAN 2005 datasets.
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.