Neural Machine Translation Doesn’t Translate Gender Coreference Right Unless You Make It

By Danielle Saunders, Rosie Sallis, Bill Byrne. 2020

69 citations recorded by the source corpus.

Neural Machine Translation (NMT) has been shown to struggle with grammatical gender that is dependent on the gender of human referents, which can cause gender bias effects. Many existing approaches to this problem seek to control gender inflection in the target language by explicitly or implicitly adding a gender feature to the source sentence, usually at the sentence level. In this paper we propose schemes for incorporating explicit word-level gender inflection tags into NMT. We explore the potential of this gender-inflection controlled translation when the gender feature can be determined from a human reference, or when a test sentence can be automatically gender-tagged, assessing on English-to-Spanish and English-to-German translation. We find that simple existing approaches can over-generalize a gender-feature to multiple entities in a sentence, and suggest effective alternatives in the form of tagged coreference adaptation data. We also propose an extension to assess translations of gender-neutral entities from English given a corresponding linguistic convention, such as a non-binary inflection, in the target language.

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): “…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 al., 2020; Renduchintala and Williams, 2021; Choubey et…”
Investigating Failures of Automatic Translation in the Case of Unambiguous Gender (2021, background): “Several works aim to enrich the gender input to an MT system by adding additional gold annotation or context (Stafanovičs et al., 2020; Saunders et al., 2020; Moryossef et al., 2019).”
Improving Gender Translation Accuracy with Filtered Self-Training (2021, unknown): “biguous input or propose methods to control for gender or to augment data with gender information (Elaraby et al., 2018; Moryossef et al., 2019; Prates et al., 2018; Saunders et al., 2020; Stafanovičs et al., 2020; Vanmassenhove et al., 2018).”
Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation (2021, background): “, 2020), and some works used synthetic datasets to debias models (Saunders et al., 2020; Zhao et al., 2018).”
The practical ethics of bias reduction in machine translation: why domain adaptation is better than data debiasing (2021, unknown): “In addition, recent work by Saunders et al (2020) extends some of the adaptation work mentioned in this article.”
First the Worst: Finding Better Gender Translations During Beam Search (2021, methodology): “Token- 071 level source gender tags are used by Stafanovičs 072 et al. (2020) and Saunders et al. (2020).”
Gender Bias in Machine Translation (2021, background): “, 2021) and one in MT (Saunders et al., 2020), the discussion around gender bias has been reduced to the binary masculine/feminine dichotomy.”