Variation and Instability in Dialect-Based Embedding Spaces

dc.contributor.authorDunn, Jonathan
dc.date.accessioned2023-04-19T23:21:54Z
dc.date.available2023-04-19T23:21:54Z
dc.date.issued2023en
dc.date.updated2023-04-13T03:27:57Z
dc.description.abstractThis paper measures variation in embedding spaces which have been trained on different regional varieties of English while controlling for instability in the embeddings. While previous work has shown that it is possible to distinguish between similar varieties of a language, this paper experiments with two follow-up questions: First, does the variety represented in the training data systematically influence the resulting embedding space after training? This paper shows that differences in embeddings across varieties are significantly higher than baseline instability. Second, is such dialectbased variation spread equally throughout the lexicon? This paper shows that specific parts of the lexicon are particularly subject to variation. Taken together, these experiments confirm that embedding spaces are significantly influenced by the dialect represented in the training data. This finding implies that there is semantic variation across dialects, in addition to previously studied lexical and syntactic variation.en
dc.identifier.citationDunn J (2023). Variation and Instability in Dialect-Based Embedding Spaces. Proceedings of the Workshop on NLP for Similar Languages, Varieties and Dialects.en
dc.identifier.doihttp://doi.org/10.48550/arXiv.2303.14963
dc.identifier.urihttps://hdl.handle.net/10092/105359
dc.language.isoenen
dc.publisherAssociation for Computational Linguisticsen
dc.rightsAll rights reserved unless otherwise stateden
dc.rights.urihttp://hdl.handle.net/10092/17651en
dc.subject.anzsrcFields of Research::47 - Language, communication and culture::4704 - Linguistics::470403 - Computational linguisticsen
dc.titleVariation and Instability in Dialect-Based Embedding Spacesen
dc.typeConference Contributions - Publisheden
uc.collegeFaculty of Arts
uc.departmentLanguage, Social and Political Sciences
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Dunn.VarDial_2023.pdf
Size:
426.31 KB
Format:
Adobe Portable Document Format
Description:
Accepted version