Semantic dependency parsing using N-best semantic role sequences and roleset information

Joo Young Lee, Han Cheol Cho, Hae-Chang Rim

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

Abstract

In this paper, we describe a syntactic and semantic dependency parsing system submitted to the shared task of CoNLL 2008. The proposed system consists of five modules: syntactic dependency parser, predicate identifier, local semantic role labeler, global role sequence candidate generator, and role sequence selector. The syntactic dependency parser is based on Malt Parser and the sequence candidate generator is based on CKY style algorithm. The remaining three modules are implemented by using maximum entropy classifiers. The proposed system achieves 76.90 of labeled F1 for the overall task, 84.82 of labeled attachment, and 68.71 of labeled F1 on the WSJ+Brown test set.

Original languageEnglish
Title of host publicationCoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning
Pages233-237
Number of pages5
Publication statusPublished - 2008 Dec 1
Event12th Conference on Computational Natural Language Learning, CoNLL 2008 - Manchester, United Kingdom
Duration: 2008 Aug 162008 Aug 17

Other

Other12th Conference on Computational Natural Language Learning, CoNLL 2008
CountryUnited Kingdom
CityManchester
Period08/8/1608/8/17

Fingerprint

Syntactics
Semantics
semantics
candidacy
entropy
Classifiers
Entropy

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Linguistics and Language

Cite this

Lee, J. Y., Cho, H. C., & Rim, H-C. (2008). Semantic dependency parsing using N-best semantic role sequences and roleset information. In CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning (pp. 233-237)

Semantic dependency parsing using N-best semantic role sequences and roleset information. / Lee, Joo Young; Cho, Han Cheol; Rim, Hae-Chang.

CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. 2008. p. 233-237.

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

Lee, JY, Cho, HC & Rim, H-C 2008, Semantic dependency parsing using N-best semantic role sequences and roleset information. in CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. pp. 233-237, 12th Conference on Computational Natural Language Learning, CoNLL 2008, Manchester, United Kingdom, 08/8/16.
Lee JY, Cho HC, Rim H-C. Semantic dependency parsing using N-best semantic role sequences and roleset information. In CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. 2008. p. 233-237
Lee, Joo Young ; Cho, Han Cheol ; Rim, Hae-Chang. / Semantic dependency parsing using N-best semantic role sequences and roleset information. CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning. 2008. pp. 233-237
@inproceedings{524e3b3270cd44db81ba9a606a45a300,
title = "Semantic dependency parsing using N-best semantic role sequences and roleset information",
abstract = "In this paper, we describe a syntactic and semantic dependency parsing system submitted to the shared task of CoNLL 2008. The proposed system consists of five modules: syntactic dependency parser, predicate identifier, local semantic role labeler, global role sequence candidate generator, and role sequence selector. The syntactic dependency parser is based on Malt Parser and the sequence candidate generator is based on CKY style algorithm. The remaining three modules are implemented by using maximum entropy classifiers. The proposed system achieves 76.90 of labeled F1 for the overall task, 84.82 of labeled attachment, and 68.71 of labeled F1 on the WSJ+Brown test set.",
author = "Lee, {Joo Young} and Cho, {Han Cheol} and Hae-Chang Rim",
year = "2008",
month = "12",
day = "1",
language = "English",
isbn = "1905593481",
pages = "233--237",
booktitle = "CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning",

}

TY - GEN

T1 - Semantic dependency parsing using N-best semantic role sequences and roleset information

AU - Lee, Joo Young

AU - Cho, Han Cheol

AU - Rim, Hae-Chang

PY - 2008/12/1

Y1 - 2008/12/1

N2 - In this paper, we describe a syntactic and semantic dependency parsing system submitted to the shared task of CoNLL 2008. The proposed system consists of five modules: syntactic dependency parser, predicate identifier, local semantic role labeler, global role sequence candidate generator, and role sequence selector. The syntactic dependency parser is based on Malt Parser and the sequence candidate generator is based on CKY style algorithm. The remaining three modules are implemented by using maximum entropy classifiers. The proposed system achieves 76.90 of labeled F1 for the overall task, 84.82 of labeled attachment, and 68.71 of labeled F1 on the WSJ+Brown test set.

AB - In this paper, we describe a syntactic and semantic dependency parsing system submitted to the shared task of CoNLL 2008. The proposed system consists of five modules: syntactic dependency parser, predicate identifier, local semantic role labeler, global role sequence candidate generator, and role sequence selector. The syntactic dependency parser is based on Malt Parser and the sequence candidate generator is based on CKY style algorithm. The remaining three modules are implemented by using maximum entropy classifiers. The proposed system achieves 76.90 of labeled F1 for the overall task, 84.82 of labeled attachment, and 68.71 of labeled F1 on the WSJ+Brown test set.

UR - http://www.scopus.com/inward/record.url?scp=84865102655&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865102655&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84865102655

SN - 1905593481

SN - 9781905593484

SP - 233

EP - 237

BT - CoNLL 2008 - Proceedings of the Twelfth Conference on Computational Natural Language Learning

ER -