How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation

Autor:	Gaido, Marco, Savoldi, Beatrice, Bentivogli, Luisa, Negri, Matteo, Turchi, Marco
Rok vydání:	2021
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	Having recognized gender bias as a major issue affecting current translation technologies, researchers have primarily attempted to mitigate it by working on the data front. However, whether algorithmic aspects concur to exacerbate unwanted outputs remains so far under-investigated. In this work, we bring the analysis on gender bias in automatic translation onto a seemingly neutral yet critical component: word segmentation. Can segmenting methods influence the ability to translate gender? Do certain segmentation approaches penalize the representation of feminine linguistic markings? We address these questions by comparing 5 existing segmentation strategies on the target side of speech translation systems. Our results on two language pairs (English-Italian/French) show that state-of-the-art sub-word splitting (BPE) comes at the cost of higher gender bias. In light of this finding, we propose a combined approach that preserves BPE overall translation quality, while leveraging the higher ability of character-based segmentation to properly translate gender. Comment: Accepted in Findings of ACL 2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2105.13782 Zobrazit plný text záznamu View this record from Arxiv