Hide metadata

dc.date.accessioned2017-09-06T10:58:16Z
dc.date.available2017-09-06T10:58:16Z
dc.date.created2017-08-31T14:26:29Z
dc.date.issued2017
dc.identifier.citationKutuzov, Andrei Velldal, Erik Øvrelid, Lilja . Tracing armed conflicts with diachronic word embedding models. Proceedings of the Events and Stories in the News Workshop. 2017, 31-36 Association for Computational Linguistics
dc.identifier.urihttp://hdl.handle.net/10852/57837
dc.description.abstractRecent studies have shown that word embedding models can be used to trace time-related (diachronic) semantic shifts for particular words. In this paper, we evaluate some of these approaches on the new task of predicting the dynamics of global armed conflicts on a year-to-year basis, using a dataset from the field of conflict re- search as the gold standard and the Gigaword news corpus as the training data. The results show that much work still remains in extracting ‘cultural’ semantic shifts from diachronic word embedding models. At the same time, we present a new task complete with an evaluation set and introduce the ‘anchor words’ method which outperforms previous approaches on this data.en_US
dc.languageEN
dc.publisherAssociation for Computational Linguistics
dc.titleTracing armed conflicts with diachronic word embedding modelsen_US
dc.typeChapteren_US
dc.creator.authorKutuzov, Andrei
dc.creator.authorVelldal, Erik
dc.creator.authorØvrelid, Lilja
cristin.unitcode185,15,5,56
cristin.unitnameForskningsgruppen for språkteknologi
cristin.ispublishedtrue
cristin.fulltextoriginal
dc.identifier.cristin1490214
dc.identifier.bibliographiccitationinfo:ofi/fmt:kev:mtx:ctx&ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.btitle=Proceedings of the Events and Stories in the News Workshop&rft.spage=31&rft.date=2017
dc.identifier.startpage31
dc.identifier.endpage36
dc.identifier.pagecount111
dc.identifier.doihttp://dx.doi.org/10.18653/v1/W17-2705
dc.identifier.urnURN:NBN:no-60571
dc.type.documentBokkapittelen_US
dc.type.peerreviewedPeer reviewed
dc.source.isbn978-1-945626-63-0
dc.identifier.fulltextFulltext https://www.duo.uio.no/bitstream/handle/10852/57837/1/W17-2705.pdf
dc.type.versionPublishedVersion
cristin.btitleProceedings of the Events and Stories in the News Workshop


Files in this item

Appears in the following Collection

Hide metadata