publication . Preprint . Article . 2020

Gender Coreference and Bias Evaluation at WMT 2020

Kocmi, Tom; Limisiewicz, Tomasz; Stanovsky, Gabriel;
Open Access English
  • Published: 12 Oct 2020
Gender bias in machine translation can manifest when choosing gender inflections based on spurious gender correlations. For example, always translating doctors as men and nurses as women. This can be particularly harmful as models become more popular and deployed within commercial systems. Our work presents the largest evidence for the phenomenon in more than 19 systems submitted to the WMT over four diverse target languages: Czech, German, Polish, and Russian. To achieve this, we use WinoMT, a recent automatic test suite which examines gender coreference and bias when translating from English to languages with grammatical gender. We extend WinoMT to handle two ...
Persistent Identifiers
free text keywords: Computer Science - Computation and Language, Computation and Language (cs.CL), FOS: Computer and information sciences
Related Organizations
Communities with gateway
OpenAIRE Connect image
Other Communities
Funded by
EC| Bergamot
Browser-based Multilingual Translation
  • Funder: European Commission (EC)
  • Project Code: 825303
  • Funding stream: H2020 | RIA
Any information missing or wrong?Report an Issue