Improving Gender Translation Accuracy with Filtered Self-Training
This addresses gender bias in machine translation for users of multilingual systems, but it is incremental as it builds on existing self-training methods.
The paper tackled the problem of incorrect gender translation in machine translation systems, which can reflect social biases, by proposing a gender-filtered self-training technique. The result showed improved gender translation accuracy without compromising generic translation quality across five languages.
Targeted evaluations have found that machine translation systems often output incorrect gender, even when the gender is clear from context. Furthermore, these incorrectly gendered translations have the potential to reflect or amplify social biases. We propose a gender-filtered self-training technique to improve gender translation accuracy on unambiguously gendered inputs. This approach uses a source monolingual corpus and an initial model to generate gender-specific pseudo-parallel corpora which are then added to the training data. We filter the gender-specific corpora on the source and target sides to ensure that sentence pairs contain and correctly translate the specified gender. We evaluate our approach on translation from English into five languages, finding that our models improve gender translation accuracy without any cost to generic translation quality. In addition, we show the viability of our approach on several settings, including re-training from scratch, fine-tuning, controlling the balance of the training data, forward translation, and back-translation.