Controlling Translation Formality Using Pre-trained Multilingual Language Models
Published in Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), 2022
Recommended citation: Controlling Translation Formality Using Pre-trained Multilingual Language Models (Rippeth et al., IWSLT 2022) https://aclanthology.org/2022.iwslt-1.30/
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.
BibTeX:
@inproceedings{rippeth-etal-2022-controlling,
title = "Controlling Translation Formality Using Pre-trained Multilingual Language Models",
author = "Rippeth, Elijah and
Agrawal, Sweta and
Carpuat, Marine",
booktitle = "Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)",
month = may,
year = "2022",
address = "Dublin, Ireland (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.iwslt-1.30",
doi = "10.18653/v1/2022.iwslt-1.30",
pages = "327--340",
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.",
}