Show simple item record

dc.contributor.authorRecchia, Gabriel
dc.contributor.authorNulty, Paul
dc.date.accessioned2018-09-29T06:09:06Z
dc.date.available2018-09-29T06:09:06Z
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/282939
dc.description.abstractPointwise mutual information (PMI), a simple measure of lexical association, is part of several algorithms used as models of lexical semantic memory. Typically, it is used as a component of more complex distributional models rather than in isolation. We show that when two simple techniques are applied—(1) down-weighting co-occurrences involving low-frequency words in order to address PMI’s so-called “frequency bias,” and (2) defining co-occurrences as counts of “events in which instances of word1 and word2 co-occur in a context” rather than “contexts in which word1 and word2 co-occur”—then PMI outperforms default parameterizations of word embedding models in terms of how closely it matches human relatedness judgments. We also identify which down-weighting techniques are most helpful. The results suggest that simple measures may be capable of modeling certain phenomena in semantic memory, and that complex models which incorporate PMI might be improved with these modifications.
dc.description.sponsorshipCambridge Centre for Digital Knowledge
dc.titleImproving a Fundamental Measure of Lexical Association
dc.typeConference Object
prism.publicationNameProceedings of the 39th Annual Meeting of the Cognitive Science Society
dc.identifier.doi10.17863/CAM.30302
dcterms.dateAccepted2017-04-11
rioxxterms.versionofrecord10.17863/CAM.30302
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2017-04-11
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.funder-project-idFoundation for the Future
pubs.conference-name39th Annual Meeting of the Cognitive Science Society
pubs.conference-start-date2017-07-27
pubs.conference-finish-date2017-07-29
rioxxterms.freetoread.startdate2019-09-28


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record