Investigating a generic paraphrase-based approach for relation extraction

Lorenza Romano; Milen Kouylekov; Idan Szpektor; Ido Dagan; Alberto Lavelli

Investigating a generic paraphrase-based approach for relation extraction

Lorenza Romano
, Milen Kouylekov
, Idan Szpektor
, Ido Dagan
, Alberto Lavelli

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

80 Scopus citations

Abstract

Unsupervised paraphrase acquisition has been an active research field in recent years, but its effective coverage and performance have rarely been evaluated. We propose a generic paraphrase-based approach for Relation Extraction (RE), aiming at a dual goal: obtaining an applicative evaluation scheme for paraphrase acquisition and obtaining a generic and largely unsupervised configuration for RE. We analyze the potential of our approach and evaluate an implemented prototype of it using an RE dataset. Our findings reveal a high potential for unsupervised paraphrase acquisition. We also identify the need for novel robust models for matching paraphrases in texts, which should address syntactic complexity and variability.

Original language	English
Title of host publication	EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	409-416
Number of pages	8
ISBN (Print)	1932432590, 9781932432596
State	Published - 2006
Event	11th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2006 - Trento, Italy Duration: 3 Apr 2006 → 7 Apr 2006

Publication series

Name	EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

Conference

Conference	11th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2006
Country/Territory	Italy
City	Trento
Period	3/04/06 → 7/04/06

Bibliographical note

Funding Information:
This work is supported by the China 863 Program and National Nature Science Foundation Committee of China under grants 2006AA01Z247, 60672016, 60502004.

Cite this

Romano, L., Kouylekov, M., Szpektor, I., Dagan, I., & Lavelli, A. (2006). Investigating a generic paraphrase-based approach for relation extraction. In EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp. 409-416). (EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference). Association for Computational Linguistics (ACL).

Romano, Lorenza ; Kouylekov, Milen ; Szpektor, Idan et al. / Investigating a generic paraphrase-based approach for relation extraction. EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2006. pp. 409-416 (EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference).

@inproceedings{38faf1e6d85e4653b4da049c892fe2ff,

title = "Investigating a generic paraphrase-based approach for relation extraction",

abstract = "Unsupervised paraphrase acquisition has been an active research field in recent years, but its effective coverage and performance have rarely been evaluated. We propose a generic paraphrase-based approach for Relation Extraction (RE), aiming at a dual goal: obtaining an applicative evaluation scheme for paraphrase acquisition and obtaining a generic and largely unsupervised configuration for RE. We analyze the potential of our approach and evaluate an implemented prototype of it using an RE dataset. Our findings reveal a high potential for unsupervised paraphrase acquisition. We also identify the need for novel robust models for matching paraphrases in texts, which should address syntactic complexity and variability.",

author = "Lorenza Romano and Milen Kouylekov and Idan Szpektor and Ido Dagan and Alberto Lavelli",

note = "Funding Information: This work is supported by the China 863 Program and National Nature Science Foundation Committee of China under grants 2006AA01Z247, 60672016, 60502004.; 11th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2006 ; Conference date: 03-04-2006 Through 07-04-2006",

year = "2006",

language = "אנגלית",

isbn = "1932432590",

series = "EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference",

publisher = "Association for Computational Linguistics (ACL)",

pages = "409--416",

booktitle = "EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference",

address = "ארצות הברית",

}

Romano, L, Kouylekov, M, Szpektor, I, Dagan, I & Lavelli, A 2006, Investigating a generic paraphrase-based approach for relation extraction. in EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 409-416, 11th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2006, Trento, Italy, 3/04/06.

Investigating a generic paraphrase-based approach for relation extraction. / Romano, Lorenza; Kouylekov, Milen; Szpektor, Idan et al.
EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2006. p. 409-416 (EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Investigating a generic paraphrase-based approach for relation extraction

AU - Romano, Lorenza

AU - Kouylekov, Milen

AU - Szpektor, Idan

AU - Dagan, Ido

AU - Lavelli, Alberto

N1 - Funding Information: This work is supported by the China 863 Program and National Nature Science Foundation Committee of China under grants 2006AA01Z247, 60672016, 60502004.

PY - 2006

Y1 - 2006

N2 - Unsupervised paraphrase acquisition has been an active research field in recent years, but its effective coverage and performance have rarely been evaluated. We propose a generic paraphrase-based approach for Relation Extraction (RE), aiming at a dual goal: obtaining an applicative evaluation scheme for paraphrase acquisition and obtaining a generic and largely unsupervised configuration for RE. We analyze the potential of our approach and evaluate an implemented prototype of it using an RE dataset. Our findings reveal a high potential for unsupervised paraphrase acquisition. We also identify the need for novel robust models for matching paraphrases in texts, which should address syntactic complexity and variability.

AB - Unsupervised paraphrase acquisition has been an active research field in recent years, but its effective coverage and performance have rarely been evaluated. We propose a generic paraphrase-based approach for Relation Extraction (RE), aiming at a dual goal: obtaining an applicative evaluation scheme for paraphrase acquisition and obtaining a generic and largely unsupervised configuration for RE. We analyze the potential of our approach and evaluate an implemented prototype of it using an RE dataset. Our findings reveal a high potential for unsupervised paraphrase acquisition. We also identify the need for novel robust models for matching paraphrases in texts, which should address syntactic complexity and variability.

UR - https://www.scopus.com/pages/publications/84858390598

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84858390598

SN - 1932432590

SN - 9781932432596

T3 - EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

SP - 409

EP - 416

BT - EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 11th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2006

Y2 - 3 April 2006 through 7 April 2006

ER -

Romano L, Kouylekov M, Szpektor I, Dagan I, Lavelli A. Investigating a generic paraphrase-based approach for relation extraction. In EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2006. p. 409-416. (EACL 2006 - 11th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference).

Investigating a generic paraphrase-based approach for relation extraction

Abstract

Publication series

Conference

Bibliographical note

Other files and links

Fingerprint

Cite this