Towards topic labeling with phrase entailment and aggregation

Yashar Mehdad, Giuseppe Carenini, Raymond T. Ng, Shafiq Rayhan Joty

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

10 Citations (Scopus)

Abstract

We propose a novel framework for topic labeling that assigns the most representative phrases for a given set of sentences covering the same topic. We build an entailment graph over phrases that are extracted from the sentences, and use the entailment relations to identify and select the most relevant phrases. We then aggregate those selected phrases by means of phrase generalization and merging. We motivate our approach by applying over conversational data, and show that our framework improves performance significantly over baseline algorithms.

Original languageEnglish
Title of host publicationNAACL HLT 2013 - 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Main Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages179-189
Number of pages11
ISBN (Print)9781937284473
Publication statusPublished - 2013
Externally publishedYes
Event2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2013 - Atlanta, United States
Duration: 9 Jun 201314 Jun 2013

Other

Other2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2013
CountryUnited States
CityAtlanta
Period9/6/1314/6/13

Fingerprint

Merging
aggregation
Labeling
Agglomeration
performance
Entailment
Graph

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science Applications
  • Linguistics and Language

Cite this

Mehdad, Y., Carenini, G., Ng, R. T., & Rayhan Joty, S. (2013). Towards topic labeling with phrase entailment and aggregation. In NAACL HLT 2013 - 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Main Conference (pp. 179-189). Association for Computational Linguistics (ACL).

Towards topic labeling with phrase entailment and aggregation. / Mehdad, Yashar; Carenini, Giuseppe; Ng, Raymond T.; Rayhan Joty, Shafiq.

NAACL HLT 2013 - 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Main Conference. Association for Computational Linguistics (ACL), 2013. p. 179-189.

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

Mehdad, Y, Carenini, G, Ng, RT & Rayhan Joty, S 2013, Towards topic labeling with phrase entailment and aggregation. in NAACL HLT 2013 - 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Main Conference. Association for Computational Linguistics (ACL), pp. 179-189, 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2013, Atlanta, United States, 9/6/13.
Mehdad Y, Carenini G, Ng RT, Rayhan Joty S. Towards topic labeling with phrase entailment and aggregation. In NAACL HLT 2013 - 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Main Conference. Association for Computational Linguistics (ACL). 2013. p. 179-189
Mehdad, Yashar ; Carenini, Giuseppe ; Ng, Raymond T. ; Rayhan Joty, Shafiq. / Towards topic labeling with phrase entailment and aggregation. NAACL HLT 2013 - 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Main Conference. Association for Computational Linguistics (ACL), 2013. pp. 179-189
@inproceedings{6556289d8ffd4e13ab57939aee7f3e5d,
title = "Towards topic labeling with phrase entailment and aggregation",
abstract = "We propose a novel framework for topic labeling that assigns the most representative phrases for a given set of sentences covering the same topic. We build an entailment graph over phrases that are extracted from the sentences, and use the entailment relations to identify and select the most relevant phrases. We then aggregate those selected phrases by means of phrase generalization and merging. We motivate our approach by applying over conversational data, and show that our framework improves performance significantly over baseline algorithms.",
author = "Yashar Mehdad and Giuseppe Carenini and Ng, {Raymond T.} and {Rayhan Joty}, Shafiq",
year = "2013",
language = "English",
isbn = "9781937284473",
pages = "179--189",
booktitle = "NAACL HLT 2013 - 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Main Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Towards topic labeling with phrase entailment and aggregation

AU - Mehdad, Yashar

AU - Carenini, Giuseppe

AU - Ng, Raymond T.

AU - Rayhan Joty, Shafiq

PY - 2013

Y1 - 2013

N2 - We propose a novel framework for topic labeling that assigns the most representative phrases for a given set of sentences covering the same topic. We build an entailment graph over phrases that are extracted from the sentences, and use the entailment relations to identify and select the most relevant phrases. We then aggregate those selected phrases by means of phrase generalization and merging. We motivate our approach by applying over conversational data, and show that our framework improves performance significantly over baseline algorithms.

AB - We propose a novel framework for topic labeling that assigns the most representative phrases for a given set of sentences covering the same topic. We build an entailment graph over phrases that are extracted from the sentences, and use the entailment relations to identify and select the most relevant phrases. We then aggregate those selected phrases by means of phrase generalization and merging. We motivate our approach by applying over conversational data, and show that our framework improves performance significantly over baseline algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84906933161&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906933161&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781937284473

SP - 179

EP - 189

BT - NAACL HLT 2013 - 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Main Conference

PB - Association for Computational Linguistics (ACL)

ER -