Concept Embedding for Information Retrieval

Abdulahhad, Karam

[conference paper]

dc.contributor.author	Abdulahhad, Karam	de
dc.contributor.editor	Pasi, Gabriella	de
dc.contributor.editor	Piwowarski, Benjamin	de
dc.contributor.editor	Azzopardi, Leif	de
dc.contributor.editor	Hanbury, Allan	de
dc.date.accessioned	2020-11-27T07:42:34Z
dc.date.available	2020-11-27T07:42:34Z
dc.date.issued	2018	de
dc.identifier.isbn	978-3-319-76941-7	de
dc.identifier.issn	1611-3349	de
dc.identifier.uri	https://www.ssoar.info/ssoar/handle/document/70719
dc.description.abstract	Concepts are used to solve the term-mismatch problem. However, we need an effective similarity measure between concepts. Word embedding presents a promising solution. We present in this study three approaches to build concepts vectors based on words vectors. We use a vector-based measure to estimate inter-concepts similarity. Our experiments show promising results. Furthermore, words and concepts become comparable. This could be used to improve conceptual indexing process.	de
dc.language	en	de
dc.publisher	Springer International Publishing	de
dc.subject.ddc	Publizistische Medien, Journalismus,Verlagswesen	de
dc.subject.ddc	News media, journalism, publishing	en
dc.subject.other	Computation and Language; Machine Learning	de
dc.title	Concept Embedding for Information Retrieval	de
dc.description.review	begutachtet (peer reviewed)	de
dc.description.review	peer reviewed	en
dc.source.collection	Advances in Information Retrieval: 40th European Conference on IR Research, ECIR 2018, Grenoble, France, March 26-29, 2018 ; Proceedings	de
dc.source.volume	10772	de
dc.publisher.country	DEU
dc.publisher.city	Cham	de
dc.source.series	Lecture Notes in Computer Science (LNCS)
dc.subject.classoz	Informationswissenschaft	de
dc.subject.classoz	Information Science	en
dc.subject.thesoz	information retrieval	de
dc.subject.thesoz	information retrieval	en
dc.subject.thesoz	Indexierung	de
dc.subject.thesoz	indexing	en
dc.identifier.urn	urn:nbn:de:0168-ssoar-70719-0
dc.rights.licence	Deposit Licence - Keine Weiterverbreitung, keine Bearbeitung	de
dc.rights.licence	Deposit Licence - No Redistribution, No Modifications	en
ssoar.contributor.institution	GESIS	de
internal.status	formal und inhaltlich fertig erschlossen	de
internal.identifier.thesoz	10047326
internal.identifier.thesoz	10047116
dc.type.stock	incollection	de
dc.type.document	Konferenzbeitrag	de
dc.type.document	conference paper	en
dc.source.pageinfo	563-569	de
internal.identifier.classoz	1080500
internal.identifier.document	16
dc.source.conference	European Conference on IR Research (ECIR)	de
dc.event.city	Grenoble	de
internal.identifier.ddc	070
dc.identifier.doi	https://doi.org/10.1007/978-3-319-76941-7_45	de
dc.date.conference	2018	de
dc.source.conferencenumber	40	de
dc.description.pubstatus	Postprint	de
dc.description.pubstatus	Postprint	en
internal.identifier.licence	3
internal.identifier.pubstatus	2
internal.identifier.review	1
internal.identifier.series	1470
ssoar.wgl.collection	true	de
internal.pdf.wellformed	true
internal.pdf.encrypted	false

Files in this item

Name:: ssoar-2018-abdulahhad-Concept_ ...
Size:: 238.3Kb
Format:: PDF

View/Open

This item appears in the following Collection(s)

Informationswissenschaft (allgemein)
Information Science (general)

Show simple item record