paper-with-me

홈 › Papers

Identifying Gender Stereotypes and Biases in Automated Translation from English to Italian using Similarity Networks

2025-02-17 · Fatemeh Mohammadi, Marta Annamaria Tamborini, Paolo Ceravolo, Costanza Nardocci, Samira Maghool

This paper is a collaborative effort between Linguistics, Law, and Computer Science to evaluate stereotypes and biases in automated translation systems. We advocate gender-neutral translation as a means to promote gender inclusion and improve the objectivity of machine translation. Our approach focuses on identifying gender bias in English-to-Italian translations. First, we define gender bias following human rights law and linguistics literature. Then we proceed by identifying gender-specific terms such as she/lei and he/lui as key elements. We then evaluate the cosine similarity between these target terms and others in the dataset to reveal the model's perception of semantic relations. Using numerical features, we effectively evaluate the intensity and direction of the bias. Our findings provide tangible insights for developing and training gender-neutral translation algorithms.

📄 PDF Abstract BibTeX arXiv:2502.11611

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

GOSt-MT: A Knowledge Graph for Occupation-related Gender Biases in Machine Translation

2024-09-17 · Orfeas Menis Mastromichalakis, Giorgos Filandrianos, Eva Tsouparopoulou, Dimitris Parsanoglou 외

Gender bias in machine translation (MT) systems poses significant challenges that often result in the reinforcement of harmful stereotypes. Especially in the labour domain where frequently occupations are inaccurately as…

Machine TranslationTranslation

Multi-Task Learning for Improving Gender Accuracy in Neural Machine Translation

2021-12-01 · ICON 2021 12 · Carlos Escolano, Graciela Ojeda, Christine Basta, Marta R. Costa-Jussa

Machine Translation is highly impacted by social biases present in data sets, indicating that it reflects and amplifies stereotypes. In this work, we study mitigating gender bias by jointly learning the translation, the …

Machine TranslationMulti-Task LearningTranslation

Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques

2019-01-10 · Joel Escudé Font, Marta R. Costa-jussà

Neural machine translation has significantly pushed forward the quality of the field. However, there are remaining big issues with the output translations and one of them is fairness. Neural models are trained on large t…

FairnessMachine TranslationTranslationWord Embeddings

Equalizing Gender Bias in Neural Machine Translation with Word Embeddings Techniques

2019-08-01 · WS 2019 8 · Joel Escud{\'e} Font, Marta R. Costa-juss{\`a}

Neural machine translation has significantly pushed forward the quality of the field. However, there are remaining big issues with the output translations and one of them is fairness. Neural models are trained on large t…

FairnessMachine TranslationTranslationWord Embeddings

Dual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation

2025-01-17 · Tomasz Limisiewicz, David Mareček, Tomáš Musil

Mitigation of biases, such as language models' reliance on gender stereotypes, is a crucial endeavor required for the creation of reliable and useful language technology. The crucial aspect of debiasing is to ensure that…

Language ModelingLanguage Modelling