paper-with-me

홈 › Papers

Measuring and Mitigating Name Biases in Neural Machine Translation

2022-05-01 · ACL 2022 5 · Jun Wang, Benjamin Rubinstein, Trevor Cohn

Neural Machine Translation (NMT) systems exhibit problematic biases, such as stereotypical gender bias in the translation of occupation terms into languages with grammatical gender. In this paper we describe a new source of bias prevalent in NMT systems, relating to translations of sentences containing person names. To correctly translate such sentences, a NMT system needs to determine the gender of the name. We show that leading systems are particularly poor at this task, especially for female given names. This bias is deeper than given name gender: we show that the translation of terms with ambiguous sentiment can also be affected by person names, and the same holds true for proper nouns denoting race. To mitigate these biases we propose a simple but effective data augmentation method based on randomly switching entities during translation, which effectively eliminates the problem without any effect on translation quality.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationMachine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

DiBiMT: A Novel Benchmark for Measuring Word Sense Disambiguation Biases in Machine Translation

2022-05-01 · ACL 2022 5 · Niccolò Campolungo, Federico Martelli, Francesco Saina, Roberto Navigli

Lexical ambiguity poses one of the greatest challenges in the field of Machine Translation. Over the last few decades, multiple efforts have been undertaken to investigate incorrect translations caused by the polysemous …

Machine TranslationTranslationWord Sense Disambiguation

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

Measuring Sentiment Bias in Machine Translation

2023-06-12 · Kai Hartung, Aaricia Herygers, Shubham Kurlekar, Khabbab Zakaria 외

Biases induced to text by generative models have become an increasingly large topic in recent years. In this paper we explore how machine translation might introduce a bias in sentiments as classified by sentiment analys…

Machine TranslationSentiment AnalysisTranslation

Discovering and Mitigating Visual Biases through Keyword Explanation

2023-01-26 · CVPR 2024 1 · Younghyun Kim, Sangwoo Mo, Minkyu Kim, Kyungmin Lee 외

Addressing biases in computer vision models is crucial for real-world AI deployments. However, mitigating visual biases is challenging due to their unexplainable nature, often identified indirectly through visualization …

Image ClassificationImage Generation

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