N-gram and Neural Models for Uralic Language Identification: NRC at VarDial 2021

Gabriel Bernier-Colborne, Serge Leger, Cyril Goutte


Abstract
We describe the systems developed by the National Research Council Canada for the Uralic language identification shared task at the 2021 VarDial evaluation campaign. We evaluated two different approaches to this task: a probabilistic classifier exploiting only character 5-grams as features, and a character-based neural network pre-trained through self-supervision, then fine-tuned on the language identification task. The former method turned out to perform better, which casts doubt on the usefulness of deep learning methods for language identification, where they have yet to convincingly and consistently outperform simpler and less costly classification algorithms exploiting n-gram features.
Anthology ID:
2021.vardial-1.15
Volume:
Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects
Month:
April
Year:
2021
Address:
Kiyv, Ukraine
Editors:
Marcos Zampieri, Preslav Nakov, Nikola Ljubešić, Jörg Tiedemann, Yves Scherrer, Tommi Jauhiainen
Venue:
VarDial
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
128–134
Language:
URL:
https://aclanthology.org/2021.vardial-1.15
DOI:
Bibkey:
Cite (ACL):
Gabriel Bernier-Colborne, Serge Leger, and Cyril Goutte. 2021. N-gram and Neural Models for Uralic Language Identification: NRC at VarDial 2021. In Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects, pages 128–134, Kiyv, Ukraine. Association for Computational Linguistics.
Cite (Informal):
N-gram and Neural Models for Uralic Language Identification: NRC at VarDial 2021 (Bernier-Colborne et al., VarDial 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2021.vardial-1.15.pdf