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.
%0 Conference Paper
%1 troiano20:_lost_back_trans
%A Troiano, Enrica
%A Klinger, Roman
%A Padó, Sebastian
%B Proceedings of COLING
%C Online
%D 2020
%K conference myown
%T Lost in Backtranslation: Emotion Preservation in Neural Machine Translation
%U https://www.aclweb.org/anthology/2020.coling-main.384/
%X 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.
@inproceedings{troiano20:_lost_back_trans,
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.},
added-at = {2020-09-30T20:30:13.000+0200},
address = {Online},
author = {Troiano, Enrica and Klinger, Roman and Padó, Sebastian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/22499813b5bc2b1640c364ca880e35c2a/sp},
booktitle = {Proceedings of COLING},
interhash = {440a181985303a1b360b4d383c68e792},
intrahash = {2499813b5bc2b1640c364ca880e35c2a},
keywords = {conference myown},
timestamp = {2020-12-07T15:40:50.000+0100},
title = {Lost in Backtranslation: Emotion Preservation in Neural Machine Translation},
url = {https://www.aclweb.org/anthology/2020.coling-main.384/},
year = 2020
}
