Show simple item record

dc.contributor.authorEmerson, Guyen
dc.contributor.authorCopestake, Annen
dc.date.accessioned2017-01-16T09:16:13Z
dc.date.available2017-01-16T09:16:13Z
dc.date.issued2016-08-11en
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/261866
dc.description.abstractVector space models have become popular in distributional semantics, despite the challenges they face in capturing various semantic phenomena. We propose a novel probabilistic framework which draws on both formal semantics and recent advances in machine learning. In particular, we separate predicates from the entities they refer to, allowing us to perform Bayesian inference based on logical forms. We describe an implementation of this framework using a combination of Restricted Boltzmann Machines and feedforward neural networks. Finally, we demonstrate the feasibility of this approach by training it on a parsed corpus and evaluating it on established similarity datasets.
dc.language.isoenen
dc.publisherThe Association for Computational Linguistics
dc.rightsAttribution 4.0 Internationalen
dc.rightsAttribution 4.0 Internationalen
dc.rightsAttribution 4.0 Internationalen
dc.rightsAttribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.titleFunctional Distributional Semanticsen
dc.typeConference Object
prism.endingPage52
prism.numberW16-1605en
prism.publicationDate2016en
prism.publicationNameProceedings of the 1st Workshop on Representation Learning for NLPen
prism.startingPage40
dc.identifier.doi10.17863/CAM.7097
dcterms.dateAccepted2016-06-08en
rioxxterms.versionofrecord10.18653/v1/W16-1605en
rioxxterms.versionVoRen
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by/4.0/en
rioxxterms.licenseref.startdate2016-08-11en
dc.contributor.orcidEmerson, Guy [0000-0002-3136-9682]
dc.contributor.orcidCopestake, Ann [0000-0003-0347-946X]
rioxxterms.typeConference Paper/Proceeding/Abstracten
pubs.conference-name1st Workshop on Representation Learning for NLPen
pubs.conference-start-date2016-08-11en
cam.orpheus.successThu Nov 05 11:56:36 GMT 2020 - The item has an open VoR version.*
rioxxterms.freetoread.startdate2100-01-01


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's licence is described as Attribution 4.0 International