Show simple item record

dc.contributor.authorRohanian, Omid
dc.contributor.authorTaslimipoor, Shiva
dc.contributor.authorKouchaki, Samaneh
dc.contributor.authorHa, Le An
dc.contributor.authorMitkov, Ruslan
dc.date.accessioned2019-05-28T10:55:28Z
dc.date.available2019-05-28T10:55:28Z
dc.date.issued2019-06-05
dc.identifier.citationRohanian, O., Taslimipoor, S., Kouchaki, S., Ha, L. A. and Mitkov, R. (2019) Bridging the gap: attending to discontinuity in identification of multiword expressions, in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Minneapolis, Minnesota: Association for Computational Linguistics, pp. 2692–2698.en
dc.identifier.doi10.18653/v1/N19-1275
dc.identifier.urihttp://hdl.handle.net/2436/622369
dc.description.abstractWe introduce a new method to tag Multiword Expressions (MWEs) using a linguistically interpretable language-independent deep learning architecture. We specifically target discontinuity, an under-explored aspect that poses a significant challenge to computational treatment of MWEs. Two neural architectures are explored: Graph Convolutional Network (GCN) and multi-head self-attention. GCN leverages dependency parse information, and self-attention attends to long-range relations. We finally propose a combined model that integrates complementary information from both, through a gating mechanism. The experiments on a standard multilingual dataset for verbal MWEs show that our model outperforms the baselines not only in the case of discontinuous MWEs but also in overall F-score.en
dc.formatapplication/PDFen
dc.formatapplication/PDFen
dc.language.isoenen
dc.publisherAssociation for Computational Linguisticsen
dc.relation.urlhttps://naacl2019.org/en
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/*
dc.subjectnatural language processingen
dc.subjectcomputational linguisticsen
dc.subjectneural networksen
dc.subjectdeep learningen
dc.subjectmultiword expressionsen
dc.subjectsequence taggingen
dc.subjectgraph convolutional neural networksen
dc.subjectdiscontinuous expressionsen
dc.subjectattention networksen
dc.subjectself-attention networksen
dc.titleBridging the gap: attending to discontinuity in identification of multiword expressionsen
dc.typeConference contributionen
dc.conference.name2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)
pubs.finish-date2019-06-07
pubs.place-of-publicationMinneapolis, USA
pubs.start-date2019-06-02
dc.date.accepted2019-02-28
rioxxterms.funderUniversity of Wolverhampton
rioxxterms.identifier.projectUOW280519STen
rioxxterms.versionAMen
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en
rioxxterms.licenseref.startdate2019-06-07en
refterms.dateFCD2019-05-28T10:54:52Z
refterms.versionFCDAM
refterms.dateFOA2019-05-28T10:55:28Z


Files in this item

Thumbnail
Name:
Rohanian_et_al_Bridging_the_ga ...
Size:
480.4Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivs 3.0 United States
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivs 3.0 United States