Chinese Discourse Segmentation Based on Punctuation Marks

Yancui Li; Hongyu Feng; Wenhe Feng

Chinese Discourse Segmentation Based on Punctuation Marks

원문정보

보안공학연구지원센터(IJSIP) International Journal of Signal Processing, Image Processing and Pattern Recognition Vol.8 No.3 2015.03 pp.177-186

피인용수 : 0건 (자료제공 : 네이버학술정보)

초록

영어

This paper addresses Chinese discourse segmentation based on punctuation mark. Particularly, we propose various kinds of lexical, syntactic, position and punctuation features to train classifiers for Chinese discourse segmentation. Experimental results on CDTB (Chinese Discourse Treebank) show that our method based on punctuation mark is appropriate for Chinese discourse segmentation with 89.2% in accuracy.

Abstract
1. Introduction
2. Chinese Discourse Treebank
3. Method
  3.1. Framework
  3.2. Features
  3.3. Experiment Setting
4. Experiment Results and Analysis
  4.1. Results of All Features
  4.2. Results of Individual Features
  4.3. Error Analysis
5. Conclusion and Perspectives
Acknowledgements
References

키워드

저자정보

Yancui Li Department of Computer Science and Technology, Soochow University, Suzhou, China, 215006, Henan Institute of Science and Technology, Xinxiang, China, 453003
Hongyu Feng Henan Institute of Science and Technology, Xinxiang, China, 453003
Wenhe Feng Henan Institute of Science and Technology, Xinxiang, China, 453003, Computer School of Wuhan University, Wuhan, China, 430072

참고문헌

자료제공 : 네이버학술정보

함께 이용한 논문

※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

0개의 논문이 장바구니에 담겼습니다.

earticle