Improving Multi-Criteria Chinese Word Segmentation through Learning Sentence Representation

Chun Yi Lin, Ying-Jia Lin, CHIA-JEN YEH, Yi-Ting Li, Ching Wen Yang, Hung-Yu Kao

Submission Type: Regular Short Paper

Submission Track: Phonology, Morphology, and Word Segmentation

Keywords: Chinese Word Segmentation

Abstract: Recent Chinese word segmentation (CWS) models have shown competitive performance with pre-trained language models' knowledge. However, these models tend to learn the segmentation knowledge through in-vocabulary words rather than understanding the meaning of the entire context. To address this issue, we introduce a context-aware approach that incorporates unsupervised sentence representation learning over different dropout masks into the multi-criteria training framework. We demonstrate that our approach reaches state-of-the-art (SoTA) performance on F1 scores for six of the nine CWS benchmark datasets and out-of-vocabulary (OOV) recalls for eight of nine. Further experiments discover that substantial improvements can be brought with various sentence representation objectives.

Submission Number: 378