Lost in Back-Translation : Emotion Preservation in Neural Machine Translation
Troiano, Enrica; Klinger, Roman; Padó, Sebastian (2020): Lost in Back-Translation : Emotion Preservation in Neural Machine Translation, in: Donia Scott, Nuria Bell, Chengqing Zong, u. a. (Hrsg.), Proceedings of the 28th International Conference on Computational Linguistics, International Committee on Computational Linguistics, S. 4340–4354, doi: 10.18653/v1/2020.coling-main.384.
Details
- Fakultät/Lehrstuhl
- Autorin(nen)/Autor(en)
- Troiano, EnricaPadó, Sebastian
- Titel des Sammelwerks
- Proceedings of the 28th International Conference on Computational Linguistics
- Herausgeberin(nen)/Herausgeber des Sammelwerks
- Scott, DoniaBell, NuriaZong, Chengqing
- Konferenz
- 28th International Conference on Computational Linguistics, Barcelona, Spain (Online)
- Verlagsangabe
- International Committee on Computational Linguistics
- Erscheinungsjahr
- 2020
- Sprache(n)
- Englisch
- DOI
- Abstract
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. This paper 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.
- GND-Schlagwort(e)
- ComputerlinguistikEmotion
- Freie Schlagwort(e)
- Emotion Preservation
- DDC-Klassifikation
- 004 Computer science
- RVK-Klassifikation
- ST 306
- Dokumenttyp
- Konferenzveröffentlichung
- URI
- Datum der Freischaltung
- 14.03.2024
- Projekt(e)