Why don’t people use character-level machine translation?

Jindřich Libovický, Helmut Schmid, Alexander Fraser


Abstract
We present a literature and empirical survey that critically assesses the state of the art in character-level modeling for machine translation (MT). Despite evidence in the literature that character-level systems are comparable with subword systems, they are virtually never used in competitive setups in WMT competitions. We empirically show that even with recent modeling innovations in character-level natural language processing, character-level MT systems still struggle to match their subword-based counterparts. Character-level MT systems show neither better domain robustness, nor better morphological generalization, despite being often so motivated. However, we are able to show robustness towards source side noise and that translation quality does not degrade with increasing beam size at decoding time.
Anthology ID:
2022.findings-acl.194
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venues:
ACL | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2470–2485
Language:
URL:
https://aclanthology.org/2022.findings-acl.194
DOI:
10.18653/v1/2022.findings-acl.194
Bibkey:
Cite (ACL):
Jindřich Libovický, Helmut Schmid, and Alexander Fraser. 2022. Why don’t people use character-level machine translation?. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2470–2485, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Why don’t people use character-level machine translation? (Libovický et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.194.pdf
Software:
 2022.findings-acl.194.software.tgz