First the Worst: Finding Better Gender Translations During Beam Search

By Danielle Saunders, Rosie Sallis, Bill Byrne. 2021

38 citations recorded by the source corpus.

Generating machine translations via beam search seeks the most likely output under a model. However, beam search has been shown to amplify demographic biases exhibited by a model. We aim to address this, focusing on gender bias resulting from systematic errors in grammatical gender translation. Almost all prior work on this problem adjusts the training data or the model itself. By contrast, our approach changes only the inference procedure. We constrain beam search to improve gender diversity in n-best lists, and rerank n-best lists using gender features obtained from the source sentence. Combining these strongly improves WinoMT gender translation accuracy for three language pairs without additional bilingual data or retraining. We also demonstrate our approach’s utility for consistently gendering named entities, and its flexibility to handle new gendered language beyond the binary.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Societal Biases in Language Generation: Progress and Challenges (2021, background): “…and Byrne (2020) present a lattice rescoring procedure that creates gender-inﬂected search spaces to rescore text for more accurate translations, and Saunders et al. (2021) subsequently use this lattice structure to present more gendered options during beam search and rerank translation hypotheses…”