期刊文献+

Improving Syntactic Parsing of Chinese with Empty Element Recovery

Improving Syntactic Parsing of Chinese with Empty Element Recovery
原文传递
导出
摘要 This paper puts forward and explores the problem of empty element (EE) recovery in Chinese from the syntactic parsing perspective, which has been largely ignored in the literature. First, we demonstrate why EEs play a critical role in syntactic parsing of Chinese and how EEs can better benefit syntactic parsing of Chinese via re-categorization from the syntactic perspective. Then, we propose two ways to automatically recover EEs: a joint constituent parsing approach and a chunk-based dependency parsing approach. Evaluation on the Chinese TreeBank (CTB) 5.1 corpus shows that integrating EE recovery into the Charniak parser achieves a significant performance improvement of 1.29 in Fl-measure. To the best of our knowledge, this is the first close examination of EEs in syntactic parsing of Chinese, which deserves more attention in the future with regard to its specific importance. This paper puts forward and explores the problem of empty element (EE) recovery in Chinese from the syntactic parsing perspective, which has been largely ignored in the literature. First, we demonstrate why EEs play a critical role in syntactic parsing of Chinese and how EEs can better benefit syntactic parsing of Chinese via re-categorization from the syntactic perspective. Then, we propose two ways to automatically recover EEs: a joint constituent parsing approach and a chunk-based dependency parsing approach. Evaluation on the Chinese TreeBank (CTB) 5.1 corpus shows that integrating EE recovery into the Charniak parser achieves a significant performance improvement of 1.29 in Fl-measure. To the best of our knowledge, this is the first close examination of EEs in syntactic parsing of Chinese, which deserves more attention in the future with regard to its specific importance.
出处 《Journal of Computer Science & Technology》 SCIE EI CSCD 2013年第6期1106-1116,共11页 计算机科学技术学报(英文版)
基金 Supported by the National Natural Science Foundation of China under Grant Nos.61273320,61331011,61070123 the National High Technology Research and Development 863 Program of China under Grant No.2012AA011102
关键词 Chinese syntactic parsing empty element recovery joint constituent parsing chunk-based dependency parsing Chinese syntactic parsing, empty element recovery, joint constituent parsing, chunk-based dependency parsing
  • 相关文献

参考文献2

二级参考文献53

  • 1Soon W M, Ng H T, Lim D. A machine learning approach to coreference resolution of noun phrase. Computational Linguistics, 2001, 27(4): 521-544.
  • 2Ng V. Cardie C. Improving machine learning approaches to coreference resolution. In Proc. A CL 2002, Philadelphia, USA, Jul. 6-12, 2002, pp.104-111.
  • 3Strube M, Muller C. A machine learning approach to pronoun resolution in spoken dialogue. In Proc. ACL 2003, Sapporo, Japan, Jul. 7-12, 2003, pp.68-175.
  • 4Yang X F, Zhou G D, Su J, Chew C L. Corefcrence resolution using competition learning approach. In Proc. ACL 2003, Sapporo, Japan, Jul. 7-12, 2003, pp.177-184.
  • 5Yang X F, Su J, Lang J, Tan C L, Liu T, Li S. An entitymention model for coreference resolution with inductive logic programming. In Proc. ACL 2008, Columbus, USA, Jun. 15- 20, 2008, pp.843-851.
  • 6Paice C D, Husk G D. Towards the automatic recognition of anaphoric features i,1 English text: The impersonal pronoun it. Computer Speech and Language, 1987, 2(2): 109-132.
  • 7Lappin S, Leass H J. An algorithm for pronominal anaphora resolution. Computational Linguistics, 1994, 2(](4): 535-561.
  • 8Kennedy C, Boguraev B. Anaphora for everyone: Pronominal anaphora resolution without a parser. In Proc. COL- ING1996, Copenhagen, Denmark, Aug. 5-9, 1996, pp.113- 118.
  • 9Denber M. Automatic resolution of anaphora in English. Technical Report, Eastman Kodak Co. 1998.
  • 10Vieira R, Poesio M. An empirically based system for processing definite descriptions. Computational Linguistics, 2000, 27(4): 539-592.

共引文献6

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部