Active learning-based elicitation for semi-supervised word alignment

Vamshi Ambati, Stephan Vogel, Jaime Carbonell

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

3 Citations (Scopus)

Abstract

Semi-supervised word alignment aims to improve the accuracy of automatic word alignment by incorporating full or partial manual alignments. Motivated by standard active learning query sampling frameworks like uncertainty-, margin- and query-by-committee sampling we propose multiple query strategies for the alignment link selection task. Our experiments show that by active selection of uncertain and informative links, we reduce the overall manual effort involved in elicitation of alignment link data for training a semi-supervised word aligner.

Original languageEnglish
Title of host publicationACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Pages365-370
Number of pages6
Publication statusPublished - 1 Dec 2010
Externally publishedYes
Event48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 - Uppsala, Sweden
Duration: 11 Jul 201016 Jul 2010

Other

Other48th Annual Meeting of the Association for Computational Linguistics, ACL 2010
CountrySweden
CityUppsala
Period11/7/1016/7/10

Fingerprint

learning
uncertainty
experiment
Active Learning
Alignment
Sampling
Uncertainty
Selection Task
Experiment

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Ambati, V., Vogel, S., & Carbonell, J. (2010). Active learning-based elicitation for semi-supervised word alignment. In ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 365-370)

Active learning-based elicitation for semi-supervised word alignment. / Ambati, Vamshi; Vogel, Stephan; Carbonell, Jaime.

ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. p. 365-370.

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

Ambati, V, Vogel, S & Carbonell, J 2010, Active learning-based elicitation for semi-supervised word alignment. in ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. pp. 365-370, 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010, Uppsala, Sweden, 11/7/10.
Ambati V, Vogel S, Carbonell J. Active learning-based elicitation for semi-supervised word alignment. In ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. p. 365-370
Ambati, Vamshi ; Vogel, Stephan ; Carbonell, Jaime. / Active learning-based elicitation for semi-supervised word alignment. ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. pp. 365-370
@inproceedings{ac831648ebc246f8a96fc5da4923b1a4,
title = "Active learning-based elicitation for semi-supervised word alignment",
abstract = "Semi-supervised word alignment aims to improve the accuracy of automatic word alignment by incorporating full or partial manual alignments. Motivated by standard active learning query sampling frameworks like uncertainty-, margin- and query-by-committee sampling we propose multiple query strategies for the alignment link selection task. Our experiments show that by active selection of uncertain and informative links, we reduce the overall manual effort involved in elicitation of alignment link data for training a semi-supervised word aligner.",
author = "Vamshi Ambati and Stephan Vogel and Jaime Carbonell",
year = "2010",
month = "12",
day = "1",
language = "English",
isbn = "9781617388088",
pages = "365--370",
booktitle = "ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - Active learning-based elicitation for semi-supervised word alignment

AU - Ambati, Vamshi

AU - Vogel, Stephan

AU - Carbonell, Jaime

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Semi-supervised word alignment aims to improve the accuracy of automatic word alignment by incorporating full or partial manual alignments. Motivated by standard active learning query sampling frameworks like uncertainty-, margin- and query-by-committee sampling we propose multiple query strategies for the alignment link selection task. Our experiments show that by active selection of uncertain and informative links, we reduce the overall manual effort involved in elicitation of alignment link data for training a semi-supervised word aligner.

AB - Semi-supervised word alignment aims to improve the accuracy of automatic word alignment by incorporating full or partial manual alignments. Motivated by standard active learning query sampling frameworks like uncertainty-, margin- and query-by-committee sampling we propose multiple query strategies for the alignment link selection task. Our experiments show that by active selection of uncertain and informative links, we reduce the overall manual effort involved in elicitation of alignment link data for training a semi-supervised word aligner.

UR - http://www.scopus.com/inward/record.url?scp=84859945555&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859945555&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781617388088

SP - 365

EP - 370

BT - ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

ER -