paper-with-me

홈 › Papers

Evaluating Gender Bias in German Machine Translation

2025-02-26 · Michelle Kappl

We present WinoMTDE, a new gender bias evaluation test set designed to assess occupational stereotyping and underrepresentation in German machine translation (MT) systems. Building on the automatic evaluation method introduced by arXiv:1906.00591v1 [cs.CL], we extend the approach to German, a language with grammatical gender. The WinoMTDE dataset comprises 288 German sentences that are balanced in regard to gender, as well as stereotype, which was annotated using German labor statistics. We conduct a large-scale evaluation of five widely used MT systems and a large language model. Our results reveal persistent bias in most models, with the LLM outperforming traditional systems. The dataset and evaluation code are publicly available under https://github.com/michellekappl/mt_gender_german.

📄 PDF Abstract BibTeX arXiv:2502.19104

Code (1)

michellekappl/mt_gender_german 공식 구현

Tasks

Language ModelingLanguage ModellingLarge Language ModelMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

GG-BBQ: German Gender Bias Benchmark for Question Answering

2025-07-22 · Shalaka Satheesh, Katrin Klug, Katharina Beckh, Héctor Allende-Cid 외 arxiv

Within the context of Natural Language Processing (NLP), fairness evaluation is often associated with the assessment of bias and reduction of associated harm. In this regard, the evaluation is usually carried out by usin…

Machine TranslationQuestion Answering

Building Bridges: A Dataset for Evaluating Gender-Fair Machine Translation into German

2024-06-10 · Manuel Lardelli, Giuseppe Attanasio, Anne Lauscher

The translation of gender-neutral person-referring terms (e.g., the students) is often non-trivial. Translating from English into German poses an interesting case -- in German, person-referring nouns are usually gender-s…

Machine TranslationSentenceTranslation

Does Context Help Mitigate Gender Bias in Neural Machine Translation?

2024-06-18 · Harritxu Gete, Thierry Etchegoyhen

Neural Machine Translation models tend to perpetuate gender bias present in their training data distribution. Context-aware models have been previously suggested as a means to mitigate this type of bias. In this work, we…

Machine TranslationTranslation

Mitigating Gender Bias in Machine Translation through Adversarial Learning

2022-03-20 · Eve Fleisig, Christiane Fellbaum

Machine translation and other NLP systems often contain significant biases regarding sensitive attributes, such as gender or race, that worsen system performance and perpetuate harmful stereotypes. Recent preliminary res…

Machine TranslationTranslation

Mitigating Gender Bias in Machine Translation through Adversarial Learning

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Machine translation and other NLP systems often contain significant biases regarding sensitive attributes, such as gender or race, that worsen system performance and perpetuate harmful stereotypes. Recent preliminary res…

Machine TranslationTranslation