Improving Multi-Criteria Chinese Word Segmentation through Learning Sentence Representation
Chun Lin, Ying-Jia Lin, Chia-Jen Yeh, Yiting Li, Ching Yang, Hung‐Yu Kao · 2023
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-theart (SoTA) performance on F1 scores for six of the nine CWS benchmark datasets and outof-vocabulary (OOV) recalls for eight of nine.Further experiments discover that substantial improvements can be brought with various sentence representation objectives.