A Machine Learning Approach to Determine Semantic Dependency Structure in Chinese

Jiajun Yan, David B. Bracewell, Fuji Ren, Shingo Kuroiwa

In this paper, we attempt to automatically annotate the Penn Chinese Treebank with semantic dependency structure. Initially a small portion of the Penn Chinese Treebank was manually annotated with headword and semantic dependency relations. An initial investigation is then done using a Naive Bayesian Classifier and some handcrafted rules. The results show that the algorithms and proposed approach are effective at determining semantic dependency structure automatically. The Naive Bayesian Classifier makes a good baseline algorithm for future research.

Subjects: 13. Natural Language Processing; 12. Machine Learning and Discovery

Submitted: Jan 31, 2006

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.