paper-with-me

홈 › Papers

Gender Coreference and Bias Evaluation at WMT 2020

2020-10-12 · WMT (EMNLP) 2020 11 · Tom Kocmi, Tomasz Limisiewicz, Gabriel Stanovsky

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 new languages tested in WMT: Polish and Czech. We find that all systems consistently use spurious correlations in the data rather than meaningful contextual information.

📄 PDF Abstract BibTeX arXiv:2010.06018

Code (2)

gabrielStanovsky/mt_gender
michellekappl/mt_gender_german

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods

2018-04-18 · NAACL 2018 6 · Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez 외

We introduce a new benchmark, WinoBias, for coreference resolution focused on gender bias. Our corpus contains Winograd-schema style sentences with entities corresponding to people referred by their occupation (e.g. the …

coreference-resolutionCoreference ResolutionData Augmentation

Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation

2021-09-08 · Findings (EMNLP) 2021 11 · Shahar Levy, Koren Lazar, Gabriel Stanovsky

Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do …

coreference-resolutionCoreference ResolutionDiagnosticMachine Translation+1

Gender Bias in Coreference Resolution

2018-04-25 · NAACL 2018 6 · Rachel Rudinger, Jason Naradowsky, Brian Leonard, Benjamin Van Durme

We present an empirical study of gender bias in coreference resolution systems. We first introduce a novel, Winograd schema-style set of minimal pair sentences that differ only by pronoun gender. With these "Winogender s…

coreference-resolutionCoreference Resolution

Transforming Dutch: Debiasing Dutch Coreference Resolution Systems for Non-binary Pronouns

2024-04-30 · Goya van Boven, Yupei Du, Dong Nguyen

Gender-neutral pronouns are increasingly being introduced across Western languages. Recent evaluations have however demonstrated that English NLP systems are unable to correctly process gender-neutral pronouns, with the …

coreference-resolutionCoreference ResolutioncounterfactualData Augmentation

WinoPron: Revisiting English Winogender Schemas for Consistency, Coverage, and Grammatical Case

2024-09-09 · Vagrant Gautam, Julius Steuer, Eileen Bingert, Ray Johns 외

While measuring bias and robustness in coreference resolution are important goals, such measurements are only as good as the tools we use to measure them. Winogender Schemas (Rudinger et al., 2018) are an influential dat…

coreference-resolutionCoreference ResolutionLanguage Modelling