Paraphrase to explicate: Revealing implicit noun-compound relations

Vered Shwartz; Ido Dagan

doi:10.18653/v1/p18-1111

Paraphrase to explicate: Revealing implicit noun-compound relations

Vered Shwartz, Ido Dagan

Department of Computer Science

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

19 Scopus citations

Abstract

Revealing the implicit semantic relation between the constituents of a noun-compound is important for many NLP applications. It has been addressed in the literature either as a classification task to a set of pre-defined relations or by producing free text paraphrases explicating the relations. Most existing paraphrasing methods lack the ability to generalize, and have a hard time interpreting infrequent or new noun-compounds. We propose a neural model that generalizes better by representing paraphrases in a continuous space, generalizing for both unseen noun-compounds and rare paraphrases. Our model helps improving performance on both the noun-compound paraphrasing and classification tasks.

Original language	English
Title of host publication	ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Publisher	Association for Computational Linguistics (ACL)
Pages	1200-1211
Number of pages	12
ISBN (Electronic)	9781948087322
DOIs	https://doi.org/10.18653/v1/p18-1111
State	Published - 2018
Event	56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia Duration: 15 Jul 2018 → 20 Jul 2018

Publication series

Name	ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume	1

Conference

Conference	56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Country/Territory	Australia
City	Melbourne
Period	15/07/18 → 20/07/18

Bibliographical note

Publisher Copyright:
© 2018 Association for Computational Linguistics

Funding

This work was supported in part by an Intel ICRI-CI grant, the Israel Science Foundation grant 1951/17, the German Research Foundation through the German-Israeli Project Cooperation (DIP, grant DA 1600/1-1), and Theo Hoffenberg. Vered is also supported by the Clore Scholars Pro-gramme (2017), and the AI2 Key Scientific Challenges Program (2017). This work was supported in part by an Intel ICRI-CI grant, the Israel Science Foundation grant 1951/17, the German Research Foundation through the German-Israeli Project Cooperation (DIP, grant DA 1600/1-1), and Theo Hoffenberg. Vered is also supported by the Clore Scholars Programme (2017), and the AI2 Key Scientific Challenges Program (2017).

Funders	Funder number
AI2 Key Scientific Challenges Program
DIP	DA 1600/1-1
German-Israeli Project Cooperation
Intel ICRI-CI
Deutsche Forschungsgemeinschaft	1600/1-1
Israel Science Foundation	1951/17

Access to Document

10.18653/v1/p18-1111

Cite this

Shwartz, V., & Dagan, I. (2018). Paraphrase to explicate: Revealing implicit noun-compound relations. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (pp. 1200-1211). (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p18-1111

Shwartz, Vered ; Dagan, Ido. / Paraphrase to explicate : Revealing implicit noun-compound relations. ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL), 2018. pp. 1200-1211 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).

@inproceedings{37e5e8e8c03f4649bedc5be777d09b62,

title = "Paraphrase to explicate: Revealing implicit noun-compound relations",

abstract = "Revealing the implicit semantic relation between the constituents of a noun-compound is important for many NLP applications. It has been addressed in the literature either as a classification task to a set of pre-defined relations or by producing free text paraphrases explicating the relations. Most existing paraphrasing methods lack the ability to generalize, and have a hard time interpreting infrequent or new noun-compounds. We propose a neural model that generalizes better by representing paraphrases in a continuous space, generalizing for both unseen noun-compounds and rare paraphrases. Our model helps improving performance on both the noun-compound paraphrasing and classification tasks.",

author = "Vered Shwartz and Ido Dagan",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 ; Conference date: 15-07-2018 Through 20-07-2018",

year = "2018",

doi = "10.18653/v1/p18-1111",

language = "אנגלית",

series = "ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

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

pages = "1200--1211",

booktitle = "ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

address = "ארצות הברית",

}

Shwartz, V & Dagan, I 2018, Paraphrase to explicate: Revealing implicit noun-compound relations. in ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), vol. 1, Association for Computational Linguistics (ACL), pp. 1200-1211, 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, 15/07/18. https://doi.org/10.18653/v1/p18-1111

Paraphrase to explicate: Revealing implicit noun-compound relations. / Shwartz, Vered; Dagan, Ido.
ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL), 2018. p. 1200-1211 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1).

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

TY - GEN

T1 - Paraphrase to explicate

T2 - 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018

AU - Shwartz, Vered

AU - Dagan, Ido

PY - 2018

Y1 - 2018

N2 - Revealing the implicit semantic relation between the constituents of a noun-compound is important for many NLP applications. It has been addressed in the literature either as a classification task to a set of pre-defined relations or by producing free text paraphrases explicating the relations. Most existing paraphrasing methods lack the ability to generalize, and have a hard time interpreting infrequent or new noun-compounds. We propose a neural model that generalizes better by representing paraphrases in a continuous space, generalizing for both unseen noun-compounds and rare paraphrases. Our model helps improving performance on both the noun-compound paraphrasing and classification tasks.

AB - Revealing the implicit semantic relation between the constituents of a noun-compound is important for many NLP applications. It has been addressed in the literature either as a classification task to a set of pre-defined relations or by producing free text paraphrases explicating the relations. Most existing paraphrasing methods lack the ability to generalize, and have a hard time interpreting infrequent or new noun-compounds. We propose a neural model that generalizes better by representing paraphrases in a continuous space, generalizing for both unseen noun-compounds and rare paraphrases. Our model helps improving performance on both the noun-compound paraphrasing and classification tasks.

UR - http://www.scopus.com/inward/record.url?scp=85057761844&partnerID=8YFLogxK

U2 - 10.18653/v1/p18-1111

DO - 10.18653/v1/p18-1111

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

AN - SCOPUS:85057761844

T3 - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

SP - 1200

EP - 1211

BT - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

PB - Association for Computational Linguistics (ACL)

Y2 - 15 July 2018 through 20 July 2018

ER -

Shwartz V, Dagan I. Paraphrase to explicate: Revealing implicit noun-compound relations. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL). 2018. p. 1200-1211. (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)). doi: 10.18653/v1/p18-1111

Paraphrase to explicate: Revealing implicit noun-compound relations

Abstract

Publication series

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this