Collaborative entity extraction and translation

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

Abstract

Entity extraction is the task of identifying names and nominal phrases ('mentions') in a text and linking coreferring mentions. We propose the use of a new source of data for improving entity extraction: the information gleaned from large bitexts and captured by a statistical, phrase-based machine translation system. We translate the individual mentions and test properties of the translated mentions, as well as comparing the translations of coreferring mentions. The results provide feedback to improve source language entity extraction. Experiments on Chinese and English show that this approach can significantly improve Chinese entity extraction (2.2%-relative improvement in name tagging F-measure, representing a 15.0% error reduction), as well as Chinese to English entity translation (9.1% relative improvement in F-measure), over state-of-the-art entity extraction and machine translation systems.

Original languageEnglish (US)
Title of host publicationInternational Conference Recent Advances in Natural Language Processing, RANLP 2007 - Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages303-309
Number of pages7
Volume2007-January
ISBN (Print)9789549174373
StatePublished - 2007
EventInternational Conference Recent Advances in Natural Language Processing, RANLP 2007 - Borovets, Bulgaria
Duration: Sep 27 2007Sep 29 2007

Other

OtherInternational Conference Recent Advances in Natural Language Processing, RANLP 2007
CountryBulgaria
CityBorovets
Period9/27/079/29/07

Fingerprint

Feedback
Experiments

Keywords

  • Joint inference
  • Machine translation
  • Named entities

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software
  • Electrical and Electronic Engineering

Cite this

Ji, H., & Grishman, R. (2007). Collaborative entity extraction and translation. In International Conference Recent Advances in Natural Language Processing, RANLP 2007 - Proceedings (Vol. 2007-January, pp. 303-309). Association for Computational Linguistics (ACL).

Collaborative entity extraction and translation. / Ji, Heng; Grishman, Ralph.

International Conference Recent Advances in Natural Language Processing, RANLP 2007 - Proceedings. Vol. 2007-January Association for Computational Linguistics (ACL), 2007. p. 303-309.

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

Ji, H & Grishman, R 2007, Collaborative entity extraction and translation. in International Conference Recent Advances in Natural Language Processing, RANLP 2007 - Proceedings. vol. 2007-January, Association for Computational Linguistics (ACL), pp. 303-309, International Conference Recent Advances in Natural Language Processing, RANLP 2007, Borovets, Bulgaria, 9/27/07.
Ji H, Grishman R. Collaborative entity extraction and translation. In International Conference Recent Advances in Natural Language Processing, RANLP 2007 - Proceedings. Vol. 2007-January. Association for Computational Linguistics (ACL). 2007. p. 303-309
Ji, Heng ; Grishman, Ralph. / Collaborative entity extraction and translation. International Conference Recent Advances in Natural Language Processing, RANLP 2007 - Proceedings. Vol. 2007-January Association for Computational Linguistics (ACL), 2007. pp. 303-309
@inproceedings{007732d293f54c6f89de774f00aa47ef,
title = "Collaborative entity extraction and translation",
abstract = "Entity extraction is the task of identifying names and nominal phrases ('mentions') in a text and linking coreferring mentions. We propose the use of a new source of data for improving entity extraction: the information gleaned from large bitexts and captured by a statistical, phrase-based machine translation system. We translate the individual mentions and test properties of the translated mentions, as well as comparing the translations of coreferring mentions. The results provide feedback to improve source language entity extraction. Experiments on Chinese and English show that this approach can significantly improve Chinese entity extraction (2.2{\%}-relative improvement in name tagging F-measure, representing a 15.0{\%} error reduction), as well as Chinese to English entity translation (9.1{\%} relative improvement in F-measure), over state-of-the-art entity extraction and machine translation systems.",
keywords = "Joint inference, Machine translation, Named entities",
author = "Heng Ji and Ralph Grishman",
year = "2007",
language = "English (US)",
isbn = "9789549174373",
volume = "2007-January",
pages = "303--309",
booktitle = "International Conference Recent Advances in Natural Language Processing, RANLP 2007 - Proceedings",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Collaborative entity extraction and translation

AU - Ji, Heng

AU - Grishman, Ralph

PY - 2007

Y1 - 2007

N2 - Entity extraction is the task of identifying names and nominal phrases ('mentions') in a text and linking coreferring mentions. We propose the use of a new source of data for improving entity extraction: the information gleaned from large bitexts and captured by a statistical, phrase-based machine translation system. We translate the individual mentions and test properties of the translated mentions, as well as comparing the translations of coreferring mentions. The results provide feedback to improve source language entity extraction. Experiments on Chinese and English show that this approach can significantly improve Chinese entity extraction (2.2%-relative improvement in name tagging F-measure, representing a 15.0% error reduction), as well as Chinese to English entity translation (9.1% relative improvement in F-measure), over state-of-the-art entity extraction and machine translation systems.

AB - Entity extraction is the task of identifying names and nominal phrases ('mentions') in a text and linking coreferring mentions. We propose the use of a new source of data for improving entity extraction: the information gleaned from large bitexts and captured by a statistical, phrase-based machine translation system. We translate the individual mentions and test properties of the translated mentions, as well as comparing the translations of coreferring mentions. The results provide feedback to improve source language entity extraction. Experiments on Chinese and English show that this approach can significantly improve Chinese entity extraction (2.2%-relative improvement in name tagging F-measure, representing a 15.0% error reduction), as well as Chinese to English entity translation (9.1% relative improvement in F-measure), over state-of-the-art entity extraction and machine translation systems.

KW - Joint inference

KW - Machine translation

KW - Named entities

UR - http://www.scopus.com/inward/record.url?scp=84959055475&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959055475&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789549174373

VL - 2007-January

SP - 303

EP - 309

BT - International Conference Recent Advances in Natural Language Processing, RANLP 2007 - Proceedings

PB - Association for Computational Linguistics (ACL)

ER -