@inproceedings{abdullah_etal_vardial2020,
title = {Rediscovering the Slavic Continuum in Representations Emerging from Neural Models of Spoken Language Identification},
author = {Badr M. Abdullah and Jacek Kudera and Tania Avgustinova and Bernd M{\"o}bius and Dietrich Klakow},
url = {https://www.aclweb.org/anthology/2020.vardial-1.12},
year = {2020},
date = {2020},
booktitle = {Proceedings of the 7th Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2020)},
pages = {128-139},
publisher = {International Committee on Computational Linguistics (ICCL)},
address = {Barcelona, Spain (Online)},
abstract = {Deep neural networks have been employed for various spoken language recognition tasks, including tasks that are multilingual by definition such as spoken language identification (LID). In this paper, we present a neural model for Slavic language identification in speech signals and analyze its emergent representations to investigate whether they reflect objective measures of language relatedness or non-linguists’ perception of language similarity. While our analysis shows that the language representation space indeed captures language relatedness to a great extent, we find perceptual confusability to be the best predictor of the language representation similarity.},
pubstate = {published},
type = {inproceedings}
}