Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-10462
For citation please use:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBrandl, Stephanie-
dc.contributor.authorLassner, David-
dc.date.accessioned2020-08-17T13:18:27Z-
dc.date.available2020-08-17T13:18:27Z-
dc.date.issued2019-08-02-
dc.identifier.isbn978-1-950737-31-4-
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/11575-
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-10462-
dc.description.abstractWe propose Word Embedding Networks, a novel method that is able to learn word embeddings of individual data slices while simultaneously aligning and ordering them without feeding temporal information a priori to the model. This gives us the opportunity to analyse the dynamics in word embeddings on a large scale in a purely data-driven manner. In experiments on two different newspaper corpora, the New York Times (English) and die Zeit (German), we were able to show that time actually determines the dynamics of semantic change. However, there is by no means a uniform evolution, but instead times of faster and times of slower change.en
dc.description.sponsorshipBMBF, 01IS17058, MALT3 - MAschinelles Lernen-The Tricks of the Tradeen
dc.language.isoenen
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subject.ddc004 Datenverarbeitung; Informatikde
dc.subject.ddc410 Linguistikde
dc.subject.otherword embeddingsen
dc.subject.otherword embedding networksen
dc.subject.otherWENen
dc.subject.othermachine learningen
dc.subject.othertext corporaen
dc.subject.othersemantic changeen
dc.titleTimes Are Changing: Investigating the Pace of Language Change in Diachronic Word Embeddingsen
dc.typeConference Objecten
tub.accessrights.dnbfreeen
tub.publisher.universityorinstitutionTechnische Universität Berlinen
dc.type.versionpublishedVersionen
dcterms.bibliographicCitation.doi10.18653/v1/W19-4718en
dcterms.bibliographicCitation.proceedingstitleProceedings of the 1st International Workshop on Computational Approaches to Historical Language Changeen
dcterms.bibliographicCitation.originalpublisherplaceStroudsburg, PAen
dcterms.bibliographicCitation.pageend150en
dcterms.bibliographicCitation.pagestart146en
dcterms.bibliographicCitation.originalpublishernameAssociation for Computational Linguisticsen
Appears in Collections:FG Maschinelles Lernen » Publications

Files in This Item:
brandl_lassner_2019.pdf
Format: Adobe PDF | Size: 330.24 kB
DownloadShow Preview
Thumbnail

Item Export Bar

This item is licensed under a Creative Commons License Creative Commons