Co-regularizing character-based and word-based models for semi-supervised Chinese word segmentation
Xiaodong Zeng, Derek F. Wong, Lidia Sam Chao, Isabel M. Trancoso · 2013
This paper presents a semi-supervised Chinese word segmentation (CWS) approach that co-regularizes character-based and word-based models. Similarly to multi-view learning, the “segmentation agreements ” between the two different types of view are used to overcome the scarcity of the label information on unlabeled data. The proposed approach trains a character-based and word-based model on labeled data, respectively, as the initial models. Then, the two models are constantly updated using unlabeled examples, where the learning objective is maximizing their segmentation agreements. The a-greements are regarded as a set of valuable constraints for regularizing the learning of both models on unlabeled data. The segmentation for an input sentence is decoded by using a joint scoring function combining the two induced models. The e-valuation on the Chinese tree bank reveals that our model results in better gains over the state-of-the-art semi-supervised models reported in the literature. 1