Chinese dependency parsing with large scale automatically constructed case structures

Kun Yu, Daisuke Kawahara, Sadao Kurohashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

18 Citations (Scopus)

Abstract

This paper proposes an approach using large scale case structures, which are automatically constructed from both a small tagged corpus and a large raw corpus, to improve Chinese dependency parsing. The case structure proposed in this paper has two characteristics: (1) it relaxes the predicate of a case structure to be all types of words which behaves as a head; (2) it is not categorized by semantic roles but marked by the neighboring modifiers attached to a head. Experimental results based on Penn Chinese Tree-bank show the proposed approach achieved 87.26% on unlabeled attachment score, which significantly outperformed the baseline parser without using case structures.

Original languageEnglish
Title of host publicationColing 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference
Pages1049-1056
Number of pages8
Publication statusPublished - Dec 1 2008
Event22nd International Conference on Computational Linguistics, Coling 2008 - Manchester, United Kingdom
Duration: Aug 18 2008Aug 22 2008

Publication series

NameColing 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference
Volume1

Other

Other22nd International Conference on Computational Linguistics, Coling 2008
CountryUnited Kingdom
CityManchester
Period8/18/088/22/08

Fingerprint

Semantics
bank
semantics
Parsing

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Linguistics and Language

Cite this

Yu, K., Kawahara, D., & Kurohashi, S. (2008). Chinese dependency parsing with large scale automatically constructed case structures. In Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference (pp. 1049-1056). (Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference; Vol. 1).

Chinese dependency parsing with large scale automatically constructed case structures. / Yu, Kun; Kawahara, Daisuke; Kurohashi, Sadao.

Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference. 2008. p. 1049-1056 (Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yu, K, Kawahara, D & Kurohashi, S 2008, Chinese dependency parsing with large scale automatically constructed case structures. in Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference. Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference, vol. 1, pp. 1049-1056, 22nd International Conference on Computational Linguistics, Coling 2008, Manchester, United Kingdom, 8/18/08.
Yu K, Kawahara D, Kurohashi S. Chinese dependency parsing with large scale automatically constructed case structures. In Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference. 2008. p. 1049-1056. (Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference).
Yu, Kun ; Kawahara, Daisuke ; Kurohashi, Sadao. / Chinese dependency parsing with large scale automatically constructed case structures. Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference. 2008. pp. 1049-1056 (Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference).
@inproceedings{2dea383444d541cba402564abcd032cb,
title = "Chinese dependency parsing with large scale automatically constructed case structures",
abstract = "This paper proposes an approach using large scale case structures, which are automatically constructed from both a small tagged corpus and a large raw corpus, to improve Chinese dependency parsing. The case structure proposed in this paper has two characteristics: (1) it relaxes the predicate of a case structure to be all types of words which behaves as a head; (2) it is not categorized by semantic roles but marked by the neighboring modifiers attached to a head. Experimental results based on Penn Chinese Tree-bank show the proposed approach achieved 87.26{\%} on unlabeled attachment score, which significantly outperformed the baseline parser without using case structures.",
author = "Kun Yu and Daisuke Kawahara and Sadao Kurohashi",
year = "2008",
month = "12",
day = "1",
language = "English",
isbn = "9781905593446",
series = "Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference",
pages = "1049--1056",
booktitle = "Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - Chinese dependency parsing with large scale automatically constructed case structures

AU - Yu, Kun

AU - Kawahara, Daisuke

AU - Kurohashi, Sadao

PY - 2008/12/1

Y1 - 2008/12/1

N2 - This paper proposes an approach using large scale case structures, which are automatically constructed from both a small tagged corpus and a large raw corpus, to improve Chinese dependency parsing. The case structure proposed in this paper has two characteristics: (1) it relaxes the predicate of a case structure to be all types of words which behaves as a head; (2) it is not categorized by semantic roles but marked by the neighboring modifiers attached to a head. Experimental results based on Penn Chinese Tree-bank show the proposed approach achieved 87.26% on unlabeled attachment score, which significantly outperformed the baseline parser without using case structures.

AB - This paper proposes an approach using large scale case structures, which are automatically constructed from both a small tagged corpus and a large raw corpus, to improve Chinese dependency parsing. The case structure proposed in this paper has two characteristics: (1) it relaxes the predicate of a case structure to be all types of words which behaves as a head; (2) it is not categorized by semantic roles but marked by the neighboring modifiers attached to a head. Experimental results based on Penn Chinese Tree-bank show the proposed approach achieved 87.26% on unlabeled attachment score, which significantly outperformed the baseline parser without using case structures.

UR - http://www.scopus.com/inward/record.url?scp=80053426163&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053426163&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:80053426163

SN - 9781905593446

T3 - Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference

SP - 1049

EP - 1056

BT - Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference

ER -