Identifying Gender Stereotypes and Biases in Automated Translation from English to Italian using Similarity Networks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationTranslationSimilar Papers 제목 키워드 기반
GOSt-MT: A Knowledge Graph for Occupation-related Gender Biases in Machine Translation
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 TranslationTranslationMulti-Task Learning for Improving Gender Accuracy in Neural Machine Translation
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 LearningTranslationEqualizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques
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 EmbeddingsEqualizing Gender Bias in Neural Machine Translation with Word Embeddings Techniques
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 EmbeddingsDual Debiasing: Remove Stereotypes and Keep Factual Gender for Fair Language Modeling and Translation
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