Lost in Back-Translation: Emotion Preservation in Neural Machine Translation
Enrica Troiano, Roman Klinger, and Sebastian Padó.
Machine translation provides powerful methods to convert text between languages, and is therefore a technology enabling a multilingual world. An important part of communication, however, takes place at the non-propositional level (e.g., politeness, formality, emotions), and it is far from clear whether current MT methods properly translate this information.
In our paper, we investigates the specific hypothesis that the non-propositional level of emotions is at least partially lost in MT. We carry out a number of experiments in a back-translation setup and establish that (1) emotions are indeed partially lost during translation; (2) this tendency can be reversed almost completely with a simple re-ranking approach informed by an emotion classifier, taking advantage of diversity in the n-best list; (3) the re-ranking approach can also be applied to change emotions, obtaining a model for emotion style transfer. An in-depth qualitative analysis reveals that there are recurring linguistic changes through which emotions are toned down or amplified, such as change of modality.
Enrica Troiano, Roman Klinger, and Sebastian Padó. Lost in back-translation: Emotion preservation in neural machine translation. In Proceedings of the 28th International Conference on Computational Linguistics, 2020.
A preprint is available at: http://www.romanklinger.de/publications/TroianoKlingerPado-coling2020.pdf
Code repository: https://github.com/EnricaIMS/LostInBackTranslation