Early Guessing for Dialect Identification

Vani Kanjirangat, Tanja Samardzic, Fabio Rinaldi, Ljiljana Dolamic


Abstract
This paper deals with the problem of incre-mental dialect identification. Our goal is toreliably determine the dialect before the fullutterance is given as input. The major partof the previous research on dialect identification has been model-centric, focusing on performance. We address a new question: How much input is needed to identify a dialect? Ourapproach is a data-centric analysis that resultsin general criteria for finding the shortest inputneeded to make a plausible guess. Workingwith three sets of language dialects (Swiss German, Indo-Aryan and Arabic languages), weshow that it is possible to generalize across dialects and datasets with two input shorteningcriteria: model confidence and minimal inputlength (adjusted for the input type). The sourcecode for experimental analysis can be found atGithub.
Anthology ID:
2022.findings-emnlp.479
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6417–6426
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.479
DOI:
10.18653/v1/2022.findings-emnlp.479
Bibkey:
Cite (ACL):
Vani Kanjirangat, Tanja Samardzic, Fabio Rinaldi, and Ljiljana Dolamic. 2022. Early Guessing for Dialect Identification. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6417–6426, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Early Guessing for Dialect Identification (Kanjirangat et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.479.pdf
Video:
 https://aclanthology.org/2022.findings-emnlp.479.mp4