Identifying Gender Stereotypes and Biases in Automated Translation from English to Italian using Similarity Networks
This addresses gender stereotypes in machine translation for linguists, computer scientists, and policymakers, though it is incremental as it applies existing methods to a specific language pair.
The paper tackled gender bias in English-to-Italian automated translation by defining bias based on human rights law and linguistics, then using cosine similarity to analyze semantic relations and evaluate bias intensity and direction, providing insights for developing gender-neutral algorithms.
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.