Improving Gender Translation Accuracy with Filtered Self-Training

By Prafulla Kumar Choubey, Anna Currey, Prashant Mathur, Georgiana Dinu. 2021

11 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, 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 Natural Language Processing

Citations in the corpus

Societal Biases in Language Generation: Progress and Challenges (2021, background): “(2018) study LSTM-based encoder-decoder translation systems, and more recent works examine Transformer-based architectures (Escudé Font and Costa-jussà, 2019; Stanovsky et al., 2019; Saunders and Byrne, 2020; Saunders et al., 2020; Costa-jussà and de Jorge, 2020; Basta et al., 2020; Stafanovičs et a”