Using semantic relations to refine coreference decisions

Heng Ji, David Westbrook, Ralph Grishman

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

Abstract

We present a novel mechanism for improving reference resolution by using the output of a relation tagger to rescore coreference hypotheses. Experiments show that this new framework can improve performance on two quite different languages - English and Chinese.

Original languageEnglish (US)
Title of host publicationHLT/EMNLP 2005 - Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
Pages17-24
Number of pages8
StatePublished - 2005
EventHuman Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT - Vancouver, BC, Canada
Duration: Oct 6 2005Oct 8 2005

Other

OtherHuman Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT
CountryCanada
CityVancouver, BC
Period10/6/0510/8/05

Fingerprint

Semantics
Experiments

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Cite this

Ji, H., Westbrook, D., & Grishman, R. (2005). Using semantic relations to refine coreference decisions. In HLT/EMNLP 2005 - Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 17-24)

Using semantic relations to refine coreference decisions. / Ji, Heng; Westbrook, David; Grishman, Ralph.

HLT/EMNLP 2005 - Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. 2005. p. 17-24.

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

Ji, H, Westbrook, D & Grishman, R 2005, Using semantic relations to refine coreference decisions. in HLT/EMNLP 2005 - Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. pp. 17-24, Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT, Vancouver, BC, Canada, 10/6/05.
Ji H, Westbrook D, Grishman R. Using semantic relations to refine coreference decisions. In HLT/EMNLP 2005 - Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. 2005. p. 17-24
Ji, Heng ; Westbrook, David ; Grishman, Ralph. / Using semantic relations to refine coreference decisions. HLT/EMNLP 2005 - Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. 2005. pp. 17-24
@inproceedings{6dd0ecbf3297470d94e0c4904771ddb8,
title = "Using semantic relations to refine coreference decisions",
abstract = "We present a novel mechanism for improving reference resolution by using the output of a relation tagger to rescore coreference hypotheses. Experiments show that this new framework can improve performance on two quite different languages - English and Chinese.",
author = "Heng Ji and David Westbrook and Ralph Grishman",
year = "2005",
language = "English (US)",
pages = "17--24",
booktitle = "HLT/EMNLP 2005 - Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",

}

TY - GEN

T1 - Using semantic relations to refine coreference decisions

AU - Ji, Heng

AU - Westbrook, David

AU - Grishman, Ralph

PY - 2005

Y1 - 2005

N2 - We present a novel mechanism for improving reference resolution by using the output of a relation tagger to rescore coreference hypotheses. Experiments show that this new framework can improve performance on two quite different languages - English and Chinese.

AB - We present a novel mechanism for improving reference resolution by using the output of a relation tagger to rescore coreference hypotheses. Experiments show that this new framework can improve performance on two quite different languages - English and Chinese.

UR - http://www.scopus.com/inward/record.url?scp=44449125635&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44449125635&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:44449125635

SP - 17

EP - 24

BT - HLT/EMNLP 2005 - Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

ER -