Most modern CWS methods followed

Conclusion

This paper presents a neural framework for the task of Chinese word segmentation, which contains three main components (1) a factory to produce word representation when given its governed characters; (2) a sentence-level likelihood evaluation system for segmented sentence; (3) an efficient and effective algorithm to find the best segmentation.

This frame work makes a latest attempt to formalize word segmentation as a direct structured learning procedure in terms fo the recent distributed representation framework.

The framework remains a great of potential that can be further investigated and improved in the future.

results matching ""

    No results matching ""