“Look, some green circles!”: learning to quantify from images

Simple item page
dc.contributor.authorBoleda, Gemmaca
dc.contributor.authorSorodoc, Ionut-Teodorca
dc.contributor.authorLazaridou, Angelikica
dc.contributor.authorHerbelot, Aurélieca
dc.contributor.authorPezzelle, Sandroca
dc.contributor.authorBernardi, Raffaellaca
dc.date.accessioned2017-08-25T17:17:10Z
dc.date.available2017-08-25T17:17:10Z
dc.date.issued2016
dc.description.abstractIn this paper, we investigate whether a neural network model can learn the meaning of natural language quantifiers (no,some and all) from their use in visual contexts. We show that memory networks perform well in this task, and that explicit counting is not necessary to the system’s performance, supporting psycholinguistic evidence on the acquisition of quantifiers.en
dc.description.sponsorshipThis project has received funding from the European Unions Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 655577 (LOVe); ERC 2011 Starting Independent Research Grant n. 283554 (COMPOSES).en
dc.format.mimetypeapplication/pdf
dc.identifier.citationSorodoc I, Lazaridou A, Boleda A, Herbelot A, Pezzelle S, Bernardi R. “Look, some green circles!”: learning to quantify from images. In: Proceedings of the 5th Workshop on Vision and Language (ACL 2016). Berlin: Association for Computational Linguistics; 2016. p. 75-79.
dc.identifier.urihttp://hdl.handle.net/10230/32703
dc.language.isoeng
dc.publisherACL (Association for Computational Linguistics)ca
dc.relation.ispartofProceedings of the 5th Workshop on Vision and Language (ACL 2016). Berlin: Association for Computational Linguistics; 2016. p. 75-79
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/655577
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/FP7/283554
dc.rights© ACL, Creative Commons Attribution 4.0 License
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subject.keywordLanguage and visionen
dc.subject.keywordGroundingen
dc.subject.keywordQuantificationen
dc.subject.keywordDistributed representationsen
dc.subject.keywordSemanticsen
dc.subject.keywordComputational semanticsen
dc.subject.keywordComputational Linguisticsen
dc.subject.keywordNatural Language Processingen
dc.title“Look, some green circles!”: learning to quantify from imagesca
dc.typeinfo:eu-repo/semantics/conferenceObject
dc.type.versioninfo:eu-repo/semantics/publishedVersion

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
boleda_wkacl16_look.pdf
Size:
226.91 KB
Format:
Adobe Portable Document Format
Download

Collections

License

Rights