CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality

Maria Nadejde, Anna Currey, Benjamin Hsu, Xing Niu, Marcello Federico, Georgiana Dinu


Abstract
The machine translation (MT) task is typically formulated as that of returning a single translation for an input segment. However, in many cases, multiple different translations are valid and the appropriate translation may depend on the intended target audience, characteristics of the speaker, or even the relationship between speakers. Specific problems arise when dealing with honorifics, particularly translating from English into languages with formality markers. For example, the sentence “Are you sure?” can be translated in German as “Sind Sie sich sicher?” (formal register) or “Bist du dir sicher?” (informal). Using wrong or inconsistent tone may be perceived as inappropriate or jarring for users of certain cultures and demographics. This work addresses the problem of learning to control target language attributes, in this case formality, from a small amount of labeled contrastive data. We introduce an annotated dataset (CoCoA-MT) and an associated evaluation metric for training and evaluating formality-controlled MT models for six diverse target languages. We show that we can train formality-controlled models by fine-tuning on labeled contrastive data, achieving high accuracy (82% in-domain and 73% out-of-domain) while maintaining overall quality.
Anthology ID:
2022.findings-naacl.47
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Venues:
Findings | NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
616–632
Language:
URL:
https://aclanthology.org/2022.findings-naacl.47
DOI:
10.18653/v1/2022.findings-naacl.47
Bibkey:
Cite (ACL):
Maria Nadejde, Anna Currey, Benjamin Hsu, Xing Niu, Marcello Federico, and Georgiana Dinu. 2022. CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 616–632, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality (Nadejde et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-naacl.47.pdf
Code
 amazon-research/contrastive-controlled-mt