Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Monitoring Term Drift Based on SemanticConsistency in an Evolving Vector Field
Högskolan i Borås, Akademin för bibliotek, information, pedagogik och IT.ORCID-id: 0000-0002-1539-8256
Högskolan i Borås, Akademin för bibliotek, information, pedagogik och IT. (DIGRES)
CERTH.
CERTH.
Vise andre og tillknytning
2015 (engelsk)Inngår i: Proceedings of IJCNN-15, 2015Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Based on the Aristotelian concept of potentialityvs. actuality allowing for the study of energy and dynamics inlanguage, we propose a field approach to lexical analysis. Fallingback on the distributional hypothesis to statistically model wordmeaning, we used evolving fields as a metaphor to express timedependentchanges in a vector space model by a combinationof random indexing and evolving self-organizing maps (ESOM).To monitor semantic drifts within the observation period, anexperiment was carried out on the term space of a collection of12.8 million Amazon book reviews. For evaluation, the semanticconsistency of ESOM term clusters was compared with theirrespective neighbourhoods in WordNet, and contrasted withdistances among term vectors by random indexing. We found thatat 0.05 level of significance, the terms in the clusters showed a highlevel of semantic consistency. Tracking the drift of distributionalpatterns in the term space across time periods, we found thatconsistency decreased, but not at a statistically significant level.Our method is highly scalable, with interpretations in philosophy.

sted, utgiver, år, opplag, sider
2015.
Emneord [en]
evolving semantics, index terms, vector field, self-organizing maps, knowledge organization, digital preservation
HSV kategori
Forskningsprogram
Biblioteks- och informationsvetenskap
Identifikatorer
URN: urn:nbn:se:hb:diva-8527OAI: oai:DiVA.org:hb-8527DiVA, id: diva2:894316
Konferanse
International Joint Conference on Neural Networks
Prosjekter
PERICLES
Forskningsfinansiär
EU, FP7, Seventh Framework Programme, FP7-601138Tilgjengelig fra: 2016-01-14 Laget: 2016-01-14 Sist oppdatert: 2018-01-10bibliografisk kontrollert

Open Access i DiVA

fulltext(120 kB)459 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 120 kBChecksum SHA-512
6f60812d261ce8d1c08c03beffc9c00fe2112fd8bac7fdf35625e428f6508d4a8879675e5671372104c7ebcc6ffc2b2b9c2131936f918b2e7bbdb61a98056a41
Type fulltextMimetype application/pdf

Andre lenker

http://arxiv.org/abs/1502.01753

Søk i DiVA

Av forfatter/redaktør
Wittek, PeterDarányi, Sándor
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 459 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 1002 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf