A risk minimization framework for extractive speech summarization

Shih Hsiang Lin, Berlin Chen

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

12 Citations (Scopus)

Abstract

In this paper, we formulate extractive summarization as a risk minimization problem and propose a unified probabilistic framework that naturally combines supervised and unsupervised summarization models to inherit their individual merits as well as to overcome their inherent limitations. In addition, the introduction of various loss functions also provides the summarization framework with a flexible but systematic way to render the redundancy and coherence relationships among sentences and between sentences and the whole document, respectively. Experiments on speech summarization show that the methods deduced from our framework are very competitive with existing summarization approaches.

Original languageEnglish
Title of host publicationACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Pages79-87
Number of pages9
Publication statusPublished - 2010
Event48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 - Uppsala, Sweden
Duration: 2010 Jul 112010 Jul 16

Other

Other48th Annual Meeting of the Association for Computational Linguistics, ACL 2010
CountrySweden
CityUppsala
Period10/7/1110/7/16

Fingerprint

loss of function
redundancy
experiment
coherence
Speech Summarization
Summarization

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Lin, S. H., & Chen, B. (2010). A risk minimization framework for extractive speech summarization. In ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 79-87)

A risk minimization framework for extractive speech summarization. / Lin, Shih Hsiang; Chen, Berlin.

ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. p. 79-87.

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

Lin, SH & Chen, B 2010, A risk minimization framework for extractive speech summarization. in ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. pp. 79-87, 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010, Uppsala, Sweden, 10/7/11.
Lin SH, Chen B. A risk minimization framework for extractive speech summarization. In ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. p. 79-87
Lin, Shih Hsiang ; Chen, Berlin. / A risk minimization framework for extractive speech summarization. ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. 2010. pp. 79-87
@inproceedings{82e624d7b5e24450957eddce4cb9f71e,
title = "A risk minimization framework for extractive speech summarization",
abstract = "In this paper, we formulate extractive summarization as a risk minimization problem and propose a unified probabilistic framework that naturally combines supervised and unsupervised summarization models to inherit their individual merits as well as to overcome their inherent limitations. In addition, the introduction of various loss functions also provides the summarization framework with a flexible but systematic way to render the redundancy and coherence relationships among sentences and between sentences and the whole document, respectively. Experiments on speech summarization show that the methods deduced from our framework are very competitive with existing summarization approaches.",
author = "Lin, {Shih Hsiang} and Berlin Chen",
year = "2010",
language = "English",
isbn = "9781617388088",
pages = "79--87",
booktitle = "ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - A risk minimization framework for extractive speech summarization

AU - Lin, Shih Hsiang

AU - Chen, Berlin

PY - 2010

Y1 - 2010

N2 - In this paper, we formulate extractive summarization as a risk minimization problem and propose a unified probabilistic framework that naturally combines supervised and unsupervised summarization models to inherit their individual merits as well as to overcome their inherent limitations. In addition, the introduction of various loss functions also provides the summarization framework with a flexible but systematic way to render the redundancy and coherence relationships among sentences and between sentences and the whole document, respectively. Experiments on speech summarization show that the methods deduced from our framework are very competitive with existing summarization approaches.

AB - In this paper, we formulate extractive summarization as a risk minimization problem and propose a unified probabilistic framework that naturally combines supervised and unsupervised summarization models to inherit their individual merits as well as to overcome their inherent limitations. In addition, the introduction of various loss functions also provides the summarization framework with a flexible but systematic way to render the redundancy and coherence relationships among sentences and between sentences and the whole document, respectively. Experiments on speech summarization show that the methods deduced from our framework are very competitive with existing summarization approaches.

UR - http://www.scopus.com/inward/record.url?scp=84859990614&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859990614&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84859990614

SN - 9781617388088

SP - 79

EP - 87

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

ER -