Publication:
AI-KU: using substitute vectors and co-occurrence modeling for word sense induction and disambiguation

dc.contributor.departmentDepartment of Computer Engineering
dc.contributor.kuauthorBaşkaya, Osman
dc.contributor.kuauthorCirik, Volkan
dc.contributor.kuauthorYüret, Deniz
dc.contributor.kuprofileMaster Student
dc.contributor.kuprofileMaster Student
dc.contributor.kuprofileMaster Student
dc.contributor.kuprofileFaculty Member
dc.contributor.yokidN/A
dc.contributor.yokidN/A
dc.contributor.yokidN/A
dc.contributor.yokid179996
dc.date.accessioned2024-11-09T22:49:59Z
dc.date.issued2013
dc.description.abstractWord sense induction aims to discover different senses of a word from a corpus by using unsupervised learning approaches. Once a sense inventory is obtained for an ambiguous word, word sense discrimination approaches choose the best-fitting single sense for a given context from the induced sense inventory. However, there may not be a clear distinction between one sense and another, although for a context, more than one induced sense can be suitable. Graded word sense method allows for labeling a word in more than one sense. In contrast to the most common approach which is to apply clustering or graph partitioning on a representation of first or second order co-occurrences of a word, we propose a system that creates a substitute vector for each target word from the most likely substitutes suggested by a statistical language model. Word samples are then taken according to probabilities of these substitutes and the results of the co-occurrence model are clustered. This approach outperforms the other systems on graded word sense induction task in SemEval-2013.
dc.description.indexedbyScopus
dc.description.openaccessYES
dc.description.publisherscopeInternational
dc.description.sponsorshipThe ACL Special Interest Group on Computational Semantics (SIGSEM)
dc.description.sponsorshipThe ACL Special Interest Group on the Lexicon (SIGLEX)
dc.description.volume2
dc.identifier.doiN/A
dc.identifier.isbn9781-9372-8449-7
dc.identifier.linkhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85040566343&partnerID=40&md5=512c8f1ed3ceb85d3172ea3e57f5d3d9
dc.identifier.scopus2-s2.0-85040566343
dc.identifier.uriN/A
dc.identifier.urihttps://hdl.handle.net/20.500.14288/6571
dc.keywordsComputational linguistics
dc.keywordsNatural language processing systems
dc.keywordsCo-occurrence
dc.keywordsGraph Partitioning
dc.keywordsMost likely
dc.keywordsSecond orders
dc.keywordsSense inventories
dc.keywordsStatistical language modeling
dc.keywordsTarget words
dc.keywordsWord sense inductions
dc.keywordsSemantics
dc.languageEnglish
dc.publisherAssociation for Computational Linguistics (ACL)
dc.source*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics
dc.subjectComputer science
dc.subjectArtificial intelligence
dc.titleAI-KU: using substitute vectors and co-occurrence modeling for word sense induction and disambiguation
dc.typeConference proceeding
dspace.entity.typePublication
local.contributor.authoridN/A
local.contributor.authoridN/A
local.contributor.authoridN/A
local.contributor.authorid0000-0002-7039-0046
local.contributor.kuauthorBaşkaya, Osman
local.contributor.kuauthorSert, Enis Rıfat
local.contributor.kuauthorCirik, Volkan
local.contributor.kuauthorYüret, Deniz
local.publication.orgunit1Graduate School of Sciences and Engineering
local.publication.orgunit1College of Engineering
local.publication.orgunit2Department of Computer Engineering
local.publication.orgunit2KUIS AI (Koç University & İş Bank Artificial Intelligence Center)
relation.isOrgUnitOfPublication89352e43-bf09-4ef4-82f6-6f9d0174ebae
relation.isOrgUnitOfPublication.latestForDiscovery89352e43-bf09-4ef4-82f6-6f9d0174ebae

Files