Edinburgh Research Explorer

Abstract Meaning Representation for Paraphrase Detection

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

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

Related Edinburgh Organisations

Open Access permissions

Open

Documents

http://aclweb.org/anthology/N18-1041
Original languageEnglish
Title of host publicationThe 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Place of PublicationNew Orleans, Louisiana, USA
PublisherAssociation for Computational Linguistics
Pages442-452
Number of pages11
DOIs
Publication statusE-pub ahead of print - 6 Jun 2018
Event16th 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 20186 Jun 2018
http://naacl2018.org/

Conference

Conference16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Abbreviated titleNAACL HLT 2018
CountryUnited States
CityNew Orleans
Period1/06/186/06/18
Internet address

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.

Download statistics

No data available

ID: 55406247