Abstract
Unlike English, morphologically rich languages can reveal characteristics of speakers or their conversational partners, such as gender and number, via pronouns, morphological endings of words and syntax. When translating from English to such languages, a machine translation model needs to opt for a certain interpretation of textual context, which may lead to serious translation errors if extra-textual information is unavailable. We investigate this challenge in the English-to-Polish language direction. We focus on the underresearched problem of utilising external metadata in automatic translation of TV dialogue, proposing a case study where a wide range of approaches for controlling attributes in translation is employed in a multi-attribute scenario. The best model achieves an improvement of +5.81 chrF++/+6.03 BLEU, with other models achieving competitive performance. We additionally contribute a novel attribute-annotated dataset of Polish TV dialogue and a morphological analysis script used to evaluate attribute control in models.- Anthology ID:
- 2022.eamt-1.15
- Volume:
- Proceedings of the 23rd Annual Conference of the European Association for Machine Translation
- Month:
- June
- Year:
- 2022
- Address:
- Ghent, Belgium
- Editors:
- Helena Moniz, Lieve Macken, Andrew Rufener, Loïc Barrault, Marta R. Costa-jussà, Christophe Declercq, Maarit Koponen, Ellie Kemp, Spyridon Pilos, Mikel L. Forcada, Carolina Scarton, Joachim Van den Bogaert, Joke Daems, Arda Tezcan, Bram Vanroy, Margot Fonteyne
- Venue:
- EAMT
- SIG:
- Publisher:
- European Association for Machine Translation
- Note:
- Pages:
- 121–130
- Language:
- URL:
- https://aclanthology.org/2022.eamt-1.15
- DOI:
- Cite (ACL):
- Sebastian T. Vincent, Loïc Barrault, and Carolina Scarton. 2022. Controlling Extra-Textual Attributes about Dialogue Participants: A Case Study of English-to-Polish Neural Machine Translation. In Proceedings of the 23rd Annual Conference of the European Association for Machine Translation, pages 121–130, Ghent, Belgium. European Association for Machine Translation.
- Cite (Informal):
- Controlling Extra-Textual Attributes about Dialogue Participants: A Case Study of English-to-Polish Neural Machine Translation (Vincent et al., EAMT 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2022.eamt-1.15.pdf