Abstract Meaning Representation for Paraphrase Detection

Fuad Issa; Marco Damonte; Shay Cohen; Xiaohui Yan; Yi Chang

doi:10.18653/v1/N18-1041

Abstract Meaning Representation for Paraphrase Detection

Fuad Issa, Marco Damonte, Shay Cohen, Xiaohui Yan, Yi Chang

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

Abstract

Abstract Meaning Representation (AMR) parsing aims at abstracting away from the syntactic realization of a sentence, and denoting only its meaning in a canonical form. As such, it is ideal for paraphrase detection, a problem in which one is required to specify whether two sentences have the same meaning. We show that naïve use of AMR in paraphrase detection is not necessarily useful, and turn to describe a technique based on latent semantic analysis in combination with AMR parsing that significantly advances state-of-the-art results in paraphrase detection for the Microsoft Research Paraphrase Corpus. Our best results in the transductive setting are 86.6% for accuracy and 90.0% for F₁ measure.

Original language	English
Title of host publication	The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Place of Publication	New Orleans, Louisiana, USA
Publisher	Association for Computational Linguistics
Pages	442-452
Number of pages	11
DOIs	https://doi.org/10.18653/v1/N18-1041
Publication status	E-pub ahead of print - 6 Jun 2018
Event	16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Hyatt Regency New Orleans Hotel, New Orleans, United States Duration: 1 Jun 2018 → 6 Jun 2018 http://naacl2018.org/

Conference

Conference	16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Abbreviated title	NAACL HLT 2018
Country/Territory	United States
City	New Orleans
Period	1/06/18 → 6/06/18
Internet address	http://naacl2018.org/

Access to Document

10.18653/v1/N18-1041

naacl18paraphraseAccepted author manuscript, 487 KB

http://aclweb.org/anthology/N18-1041

Cite this

@inproceedings{6b132e2c1b80423b93783cc7959fcb29,

title = "Abstract Meaning Representation for Paraphrase Detection",

abstract = "Abstract Meaning Representation (AMR) parsing aims at abstracting away from the syntactic realization of a sentence, and denoting only its meaning in a canonical form. As such, it is ideal for paraphrase detection, a problem in which one is required to specify whether two sentences have the same meaning. We show that na{\"i}ve use of AMR in paraphrase detection is not necessarily useful, and turn to describe a technique based on latent semantic analysis in combination with AMR parsing that significantly advances state-of-the-art results in paraphrase detection for the Microsoft Research Paraphrase Corpus. Our best results in the transductive setting are 86.6% for accuracy and 90.0% for F1 measure.",

author = "Fuad Issa and Marco Damonte and Shay Cohen and Xiaohui Yan and Yi Chang",

year = "2018",

month = jun,

day = "6",

doi = "10.18653/v1/N18-1041",

language = "English",

pages = "442--452",

booktitle = "The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",

publisher = "Association for Computational Linguistics",

note = "16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 ; Conference date: 01-06-2018 Through 06-06-2018",

url = "http://naacl2018.org/",

}

Issa, F, Damonte, M, Cohen, S, Yan, X & Chang, Y 2018, Abstract Meaning Representation for Paraphrase Detection. in The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, New Orleans, Louisiana, USA, pp. 442-452, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, Louisiana, United States, 1/06/18. https://doi.org/10.18653/v1/N18-1041

Abstract Meaning Representation for Paraphrase Detection. / Issa, Fuad; Damonte, Marco; Cohen, Shay; Yan, Xiaohui; Chang, Yi.

The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. New Orleans, Louisiana, USA : Association for Computational Linguistics, 2018. p. 442-452.

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

TY - GEN

T1 - Abstract Meaning Representation for Paraphrase Detection

AU - Issa, Fuad

AU - Damonte, Marco

AU - Cohen, Shay

AU - Yan, Xiaohui

AU - Chang, Yi

PY - 2018/6/6

Y1 - 2018/6/6

N2 - Abstract Meaning Representation (AMR) parsing aims at abstracting away from the syntactic realization of a sentence, and denoting only its meaning in a canonical form. As such, it is ideal for paraphrase detection, a problem in which one is required to specify whether two sentences have the same meaning. We show that naïve use of AMR in paraphrase detection is not necessarily useful, and turn to describe a technique based on latent semantic analysis in combination with AMR parsing that significantly advances state-of-the-art results in paraphrase detection for the Microsoft Research Paraphrase Corpus. Our best results in the transductive setting are 86.6% for accuracy and 90.0% for F1 measure.

AB - Abstract Meaning Representation (AMR) parsing aims at abstracting away from the syntactic realization of a sentence, and denoting only its meaning in a canonical form. As such, it is ideal for paraphrase detection, a problem in which one is required to specify whether two sentences have the same meaning. We show that naïve use of AMR in paraphrase detection is not necessarily useful, and turn to describe a technique based on latent semantic analysis in combination with AMR parsing that significantly advances state-of-the-art results in paraphrase detection for the Microsoft Research Paraphrase Corpus. Our best results in the transductive setting are 86.6% for accuracy and 90.0% for F1 measure.

UR - http://naacl2018.org/

U2 - 10.18653/v1/N18-1041

DO - 10.18653/v1/N18-1041

M3 - Conference contribution

SP - 442

EP - 452

BT - The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

PB - Association for Computational Linguistics

CY - New Orleans, Louisiana, USA

T2 - 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Y2 - 1 June 2018 through 6 June 2018

ER -

Abstract Meaning Representation for Paraphrase Detection

Abstract

Conference

Access to Document

Other files and links

Fingerprint

SUMMA - Scalable Understanding of Mulitingual Media

Cite this

Abstract Meaning Representation for Paraphrase Detection

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Projects

SUMMA - Scalable Understanding of Mulitingual Media

Cite this