Variation and Instability in Dialect-Based Embedding Spaces

Type of content
Conference Contributions - Published
Thesis discipline
Degree name
Association for Computational Linguistics
Journal Title
Journal ISSN
Volume Title
Dunn, Jonathan

This 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.

Dunn J (2023). Variation and Instability in Dialect-Based Embedding Spaces. Proceedings of the Workshop on NLP for Similar Languages, Varieties and Dialects.
Ngā upoko tukutuku/Māori subject headings
ANZSRC fields of research
Fields of Research::47 - Language, communication and culture::4704 - Linguistics::470403 - Computational linguistics
All rights reserved unless otherwise stated