Controlling Translation Formality Using Pre-trained Multilingual Language Models

Elijah Rippeth, Sweta Agrawal, Marine Carpuat


Abstract
This paper describes the University of Maryland’s submission to the Special Task on Formality Control for Spoken Language Translation at IWSLT, which evaluates translation from English into 6 languages with diverse grammatical formality markers. We investigate to what extent this problem can be addressed with a single multilingual model, simultaneously controlling its output for target language and formality. Results show that this strategy can approach the translation quality and formality control achieved by dedicated translation models. However, the nature of the underlying pre-trained language model and of the finetuning samples greatly impact results.
Anthology ID:
2022.iwslt-1.30
Volume:
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)
Month:
May
Year:
2022
Address:
Dublin, Ireland (in-person and online)
Editors:
Elizabeth Salesky, Marcello Federico, Marta Costa-jussà
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Association for Computational Linguistics
Note:
Pages:
327–340
Language:
URL:
https://aclanthology.org/2022.iwslt-1.30
DOI:
10.18653/v1/2022.iwslt-1.30
Bibkey:
Cite (ACL):
Elijah Rippeth, Sweta Agrawal, and Marine Carpuat. 2022. Controlling Translation Formality Using Pre-trained Multilingual Language Models. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 327–340, Dublin, Ireland (in-person and online). Association for Computational Linguistics.
Cite (Informal):
Controlling Translation Formality Using Pre-trained Multilingual Language Models (Rippeth et al., IWSLT 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2022.iwslt-1.30.pdf
Data
CCMatrixParaCrawl