Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training

Nathaniel Berger, Miriam Exel, Matthias Huck, Stefan Riezler


Abstract
Supervised learning in Neural Machine Translation (NMT) standardly follows a teacher forcing paradigm where the conditioning context in the model’s prediction is constituted by reference tokens, instead of its own previous predictions. In order to alleviate this lack of exploration in the space of translations, we present a simple extension of standard maximum likelihood estimation by a contrastive marking objective. The additional training signals are extracted automatically from reference translations by comparing the system hypothesis against the reference, and used for up/down-weighting correct/incorrect tokens. The proposed new training procedure requires one additional translation pass over the training set, and does not alter the standard inference setup. We show that training with contrastive markings yields improvements on top of supervised learning, and is especially useful when learning from postedits where contrastive markings indicate human error corrections to the original hypotheses.
Anthology ID:
2023.eamt-1.8
Volume:
Proceedings of the 24th Annual Conference of the European Association for Machine Translation
Month:
June
Year:
2023
Address:
Tampere, Finland
Editors:
Mary Nurminen, Judith Brenner, Maarit Koponen, Sirkku Latomaa, Mikhail Mikhailov, Frederike Schierl, Tharindu Ranasinghe, Eva Vanmassenhove, Sergi Alvarez Vidal, Nora Aranberri, Mara Nunziatini, Carla Parra Escartín, Mikel Forcada, Maja Popovic, Carolina Scarton, Helena Moniz
Venue:
EAMT
SIG:
Publisher:
European Association for Machine Translation
Note:
Pages:
69–78
Language:
URL:
https://aclanthology.org/2023.eamt-1.8
DOI:
Bibkey:
Cite (ACL):
Nathaniel Berger, Miriam Exel, Matthias Huck, and Stefan Riezler. 2023. Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training. In Proceedings of the 24th Annual Conference of the European Association for Machine Translation, pages 69–78, Tampere, Finland. European Association for Machine Translation.
Cite (Informal):
Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training (Berger et al., EAMT 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eamt-1.8.pdf