Times Are Changing: Investigating the Pace of Language Change in Diachronic Word Embeddings
dc.contributor.author | Brandl, Stephanie | |
dc.contributor.author | Lassner, David | |
dc.date.accessioned | 2020-08-17T13:18:27Z | |
dc.date.available | 2020-08-17T13:18:27Z | |
dc.date.issued | 2019-08-02 | |
dc.description.abstract | We 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.sponsorship | BMBF, 01IS17058, MALT3 - MAschinelles Lernen-The Tricks of the Trade | en |
dc.identifier.isbn | 978-1-950737-31-4 | |
dc.identifier.uri | https://depositonce.tu-berlin.de/handle/11303/11575 | |
dc.identifier.uri | http://dx.doi.org/10.14279/depositonce-10462 | |
dc.language.iso | en | en |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | en |
dc.subject.ddc | 004 Datenverarbeitung; Informatik | de |
dc.subject.ddc | 410 Linguistik | de |
dc.subject.other | word embeddings | en |
dc.subject.other | word embedding networks | en |
dc.subject.other | WEN | en |
dc.subject.other | machine learning | en |
dc.subject.other | text corpora | en |
dc.subject.other | semantic change | en |
dc.title | Times Are Changing: Investigating the Pace of Language Change in Diachronic Word Embeddings | en |
dc.type | Conference Object | en |
dc.type.version | publishedVersion | en |
dcterms.bibliographicCitation.doi | 10.18653/v1/W19-4718 | en |
dcterms.bibliographicCitation.originalpublishername | Association for Computational Linguistics | en |
dcterms.bibliographicCitation.originalpublisherplace | Stroudsburg, PA | en |
dcterms.bibliographicCitation.pageend | 150 | en |
dcterms.bibliographicCitation.pagestart | 146 | en |
dcterms.bibliographicCitation.proceedingstitle | Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change | en |
tub.accessrights.dnb | free | en |
tub.affiliation | Fak. 4 Elektrotechnik und Informatik::Inst. Softwaretechnik und Theoretische Informatik::FG Maschinelles Lernen | de |
tub.affiliation.faculty | Fak. 4 Elektrotechnik und Informatik | de |
tub.affiliation.group | FG Maschinelles Lernen | de |
tub.affiliation.institute | Inst. Softwaretechnik und Theoretische Informatik | de |
tub.publisher.universityorinstitution | Technische Universität Berlin | en |