A Study of Style in Machine Translation: Controlling the Formality of Machine Translation Output

Xing Niu, Marianna Martindale, Marine Carpuat


Abstract
Stylistic variations of language, such as formality, carry speakers’ intention beyond literal meaning and should be conveyed adequately in translation. We propose to use lexical formality models to control the formality level of machine translation output. We demonstrate the effectiveness of our approach in empirical evaluations, as measured by automatic metrics and human assessments.
Anthology ID:
D17-1299
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2814–2819
Language:
URL:
https://aclanthology.org/D17-1299
DOI:
10.18653/v1/D17-1299
Bibkey:
Cite (ACL):
Xing Niu, Marianna Martindale, and Marine Carpuat. 2017. A Study of Style in Machine Translation: Controlling the Formality of Machine Translation Output. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2814–2819, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
A Study of Style in Machine Translation: Controlling the Formality of Machine Translation Output (Niu et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1299.pdf
Video:
 https://vimeo.com/238231330