Show simple item record

dc.contributor.authorTaslimipoor, Shiva
dc.contributor.authorRohanian, Omid
dc.contributor.authorHa, Le An
dc.date.accessioned2020-05-13T13:15:44Z
dc.date.available2020-05-13T13:15:44Z
dc.date.issued2019-08-31
dc.identifier.citationTaslimipoor, S., Rohanian, O. and Ha, L.A. (2019) Cross-lingual transfer learning and multitask learning for capturing multiword expressions, Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019), 2nd August 2019, Florence, Italy, pp. 155–161.en
dc.identifier.isbn9781950737260en
dc.identifier.doi10.18653/v1/W19-5119en
dc.identifier.urihttp://hdl.handle.net/2436/623211
dc.descriptionThis is an accepted manuscript of an article published by Association for Computational Linguistics in Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019), available online: https://www.aclweb.org/anthology/W19-5119 The accepted version of the publication may differ from the final published version.en
dc.description.abstractRecent developments in deep learning have prompted a surge of interest in the application of multitask and transfer learning to NLP problems. In this study, we explore for the first time, the application of transfer learning (TRL) and multitask learning (MTL) to the identification of Multiword Expressions (MWEs). For MTL, we exploit the shared syntactic information between MWE and dependency parsing models to jointly train a single model on both tasks. We specifically predict two types of labels: MWE and dependency parse. Our neural MTL architecture utilises the supervision of dependency parsing in lower layers and predicts MWE tags in upper layers. In the TRL scenario, we overcome the scarcity of data by learning a model on a larger MWE dataset and transferring the knowledge to a resource-poor setting in another language. In both scenarios, the resulting models achieved higher performance compared to standard neural approaches.en
dc.formatapplication/pdfen
dc.language.isoenen
dc.publisherAssociation for Computational Linguisticsen
dc.relation.urlhttps://www.aclweb.org/anthology/W19-5119/en
dc.subjecttransfer learning
dc.subjectMultiword Expressions
dc.subjectmultitask learning
dc.titleCross-lingual transfer learning and multitask learning for capturing multiword expressionsen
dc.typeConference contributionen
dc.conference.nameJoint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)
dc.conference.locationFlorence, Italy
pubs.finish-date2019-08-02
pubs.start-date2019-08-02
dc.date.accepted2019-08-01
rioxxterms.funderJiscen
rioxxterms.identifier.projectUOW13052020ORen
rioxxterms.versionAMen
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by/4.0/en
rioxxterms.licenseref.startdate2020-05-13en
dc.source.beginpage155
dc.source.endpage161
refterms.dateFCD2020-05-13T13:15:19Z
refterms.versionFCDAM
refterms.dateFOA2020-05-13T13:15:45Z


Files in this item

Thumbnail
Name:
Taslimipoor_et_al_Cross-lingua ...
Size:
502.1Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

https://creativecommons.org/licenses/by/4.0/
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by/4.0/