Part of Advances in Neural Information Processing Systems 35 (NeurIPS 2022) Datasets and Benchmarks Track
Marta Costa-jussà, Christine Basta, Oriol Domingo, André Rubungo
This paper describes the OCCGEN toolkit, which allows extracting multilingual parallel data balanced in gender within occupations. OCCGEN can extract datasets that reflect gender diversity (beyond binary) more fairly in society to be further used to explicitly mitigate occupational gender stereotypes. We propose two use cases that extract evaluation datasets for machine translation in four high-resourcelanguages from different linguistic families and in a low-resource African language. Our analysis of these use cases shows that translation outputs in high-resource languages tend to worsen in feminine subsets (compared to masculine). This can be explained because less attention is paid to the source sentence. Then, more attention is given to the target prefix overgeneralizing to the most frequent masculine forms.