Improving Chinese Word Segmentation with Description Length Gain

Explore this paper's citation graph

Summary

A novel approach to CWS is presented that utilizes description length gain (DLG), an empirical goodness measure for unsupervised word discovery, to enhancethe segmentation performance of conditional random (CRF) learning.

Type
article
Published
2007-01-01
Cited by
4
References
31

Keywords

Computer science, Artificial intelligence, Conditional random field, Segmentation, Natural language processing

References

Cited by

Related papers