A Transformer Architecture for the Prediction of Cognate Reflexes

Giuseppe G. A. Celano


Abstract
This paper presents the transformer model built to participate in the SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes. It consists of an encoder-decoder architecture with multi-head attention mechanism. Its output is concatenated with the one hot encoding of the language label of an input character sequence to predict a target character sequence. The results show that the transformer outperforms the baseline rule-based system only partially.
Anthology ID:
2022.sigtyp-1.10
Volume:
Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
Month:
July
Year:
2022
Address:
Seattle, Washington
Editors:
Ekaterina Vylomova, Edoardo Ponti, Ryan Cotterell
Venue:
SIGTYP
SIG:
SIGTYP
Publisher:
Association for Computational Linguistics
Note:
Pages:
80–85
Language:
URL:
https://aclanthology.org/2022.sigtyp-1.10
DOI:
10.18653/v1/2022.sigtyp-1.10
Bibkey:
Cite (ACL):
Giuseppe G. A. Celano. 2022. A Transformer Architecture for the Prediction of Cognate Reflexes. In Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP, pages 80–85, Seattle, Washington. Association for Computational Linguistics.
Cite (Informal):
A Transformer Architecture for the Prediction of Cognate Reflexes (Celano, SIGTYP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.sigtyp-1.10.pdf