Morphologically Aware Word-Level Translation

Paula Czarnowska, Sebastian Ruder, Ryan Cotterell, Ann Copestake


Abstract
We propose a novel morphologically aware probability model for bilingual lexicon induction, which jointly models lexeme translation and inflectional morphology in a structured way. Our model exploits the basic linguistic intuition that the lexeme is the key lexical unit of meaning, while inflectional morphology provides additional syntactic information. This approach leads to substantial performance improvements—19% average improvement in accuracy across 6 language pairs over the state of the art in the supervised setting and 16% in the weakly supervised setting. As another contribution, we highlight issues associated with modern BLI that stem from ignoring inflectional morphology, and propose three suggestions for improving the task.
Anthology ID:
2020.coling-main.256
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2847–2860
Language:
URL:
https://aclanthology.org/2020.coling-main.256
DOI:
10.18653/v1/2020.coling-main.256
Bibkey:
Cite (ACL):
Paula Czarnowska, Sebastian Ruder, Ryan Cotterell, and Ann Copestake. 2020. Morphologically Aware Word-Level Translation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2847–2860, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Morphologically Aware Word-Level Translation (Czarnowska et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.256.pdf