Is Encoder-Decoder Transformer the Shiny Hammer?

Nat Gillin


Abstract
We present an approach to multi-class classification using an encoder-decoder transformer model. We trained a network to identify French varieties using the same scripts we use to train an encoder-decoder machine translation model. With some slight modification to the data preparation and inference parameters, we showed that the same tools used for machine translation can be easily re-used to achieve competitive performance for classification. On the French Dialectal Identification (FDI) task, we scored 32.4 on weighted F1, but this is far from a simple naive bayes classifier that outperforms a neural encoder-decoder model at 41.27 weighted F1.
Anthology ID:
2022.vardial-1.9
Volume:
Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Yves Scherrer, Tommi Jauhiainen, Nikola Ljubešić, Preslav Nakov, Jörg Tiedemann, Marcos Zampieri
Venue:
VarDial
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
80–85
Language:
URL:
https://aclanthology.org/2022.vardial-1.9
DOI:
Bibkey:
Cite (ACL):
Nat Gillin. 2022. Is Encoder-Decoder Transformer the Shiny Hammer?. In Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects, pages 80–85, Gyeongju, Republic of Korea. Association for Computational Linguistics.
Cite (Informal):
Is Encoder-Decoder Transformer the Shiny Hammer? (Gillin, VarDial 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.vardial-1.9.pdf