Toxicity in Multilingual Machine Translation at Scale

By Marta Ruiz Costa-jussà, Eric Michael Smith, Christophe Ropers, Daniel Licht, Javier Ferrando, Carlos Escolano. 2022

33 citations recorded by the source corpus.

Machine Translation systems can produce different types of errors, some of which are characterized as critical or catastrophic due to the specific negative impact that they can have on users. In this paper we focus on one type of critical error: added toxicity. We evaluate and analyze added toxicity when translating a large evaluation dataset (HOLISTICBIAS, over 472k sentences, covering 13 demographic axes) from English into 164 languages. An automatic toxicity evaluation shows that added toxicity across languages varies from 0% to 5%. The output languages with the most added toxicity tend to be low-resource ones, and the demographic axes with the most added toxicity include sexual orientation, gender and sex, and ability. We also perform human evaluation on a subset of 8 translation directions, confirming the prevalence of true added toxicity. We use a measurement of the amount of source contribution to the translation, where a low source contribution implies hallucination, to interpret what causes toxicity. Making use of the input attributions allows us to explain toxicity, because the source contributions significantly correlate with toxicity for 84% of languages studied. Given our findings, our recommendations to reduce added toxicity are to curate training data to avoid mistranslations, mitigate hallucination and check unstable translations.

Subfields: Artificial Intelligence, Information Systems, Machine Translation, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Machine Translation

Citations in the corpus

Prompting PaLM for Translation: Assessing Strategies and Performance (2022, background): “There, special steps must be taken to avoid exposing users to biased or toxic outputs, which may be triggered by unconstrained prompting (Gehman et al., 2020; Costa-jussà et al., 2022).”