Show simple item record

dc.contributor.authorTaslimipoor, Shiva
dc.contributor.authorMitkov, Ruslan
dc.contributor.authorCorpas Pastor, Gloria
dc.contributor.authorFazly, Afsaneh
dc.date.accessioned2018-08-10T11:17:16Z
dc.date.available2018-08-10T11:17:16Z
dc.date.issued2018-03-21
dc.identifier.isbn9783319754871
dc.identifier.issn0302-9743
dc.identifier.urihttp://hdl.handle.net/2436/621590
dc.descriptionProceedings of the 17th International Conference on Intelligent Text Processing and Computational Linguistics, CICLing2016
dc.description.abstractDue to the limited availability of parallel data in many languages, we propose a methodology that benefits from comparable corpora to find translation equivalents for collocations (as a specific type of difficult-to-translate multi-word expressions). Finding translations is known to be more difficult for collocations than for words. We propose a method based on bilingual context extraction and build a word (distributional) representation model drawing on these bilingual contexts (bilingual English-Spanish contexts in our case). We show that the bilingual context construction is effective for the task of translation equivalent learning and that our method outperforms a simplified distributional similarity baseline in finding translation equivalents.
dc.formatapplication/PDF
dc.language.isoen
dc.publisherSpringer
dc.relation.urlhttps://link.springer.com/chapter/10.1007/978-3-319-75487-1_10
dc.subjectCollocations
dc.subjectWord Vector Representation
dc.subjectDistributional Similarity
dc.subjectComparable Corpora
dc.titleBilingual contexts from comparable corpora to mine for translations of collocations
dc.typeConference contribution
dc.identifier.journalLecture Notes in Computer Science
dc.conference.nameIntelligent Text Processing and Computational Linguistics, CICLing 2016
dc.conference.locationKonya, Turkey
pubs.finish-date2016-04-09
pubs.place-of-publicationSalmon Tower Building, New York City
pubs.start-date2016-04-03
dc.date.accepted2017-04-01
rioxxterms.funderUniversity of Wolverhampton
rioxxterms.identifier.projectUOW100818ST
rioxxterms.versionAO
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
rioxxterms.licenseref.startdate2018-03-21
refterms.dateFOA2018-08-10T11:17:16Z


Files in this item

Thumbnail
Name:
Cicling2016.pdf
Size:
197.9Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record