Gabriel Stanovsky
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Gabriel Stanovsky has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Bar Iluz
2 shared publications- David Mareček
Institute of Formal and Applied Linguistics Faculty of Mathematics and Physics Charles University Prague Czech Republic
2 shared publications Tomasz Limisiewicz
School of Computer Science Faculty of Mathematics and Physics The Hebrew University of Jerusalem Charles University in Prague
2 shared publications- Dan Bareket
Allen Institute for AI, Israel
1 shared publication - Eliya Habba
The Hebrew University of Jerusalem, Israel
1 shared publication - Renana Keydar
The Faculty of Law and the Center for Digital Humanities, Hebrew University of Jerusalem , Mount Scopus, Jerusalem 9190501
1 shared publication
Latest Publications
- Open Access
Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation
We study the effect of tokenization on gender bias in machine translation, an aspect that has been largely overlooked in previous works. Specifically, we focus on the interactions between the frequency of gendered profession names in training data, their representation in the subword tokenizer's vocabulary, and gender bias. We observe that female and non-stereotypical gender inflections of profession names (e.g., Spanish "doctora" for "female doctor") tend to be split into multiple subword tokens. Our results indicate that the imbalance of gender forms in the model's training corpus is a major factor contributing to gender bias and has a greater impact than subword splitting. We show that analyzing subword splits provides good estimates of gender-form imbalance in the training data and can be used even when the corpus is not publicly available. We also demonstrate that fine-tuning just the token embedding layer can decrease the gap in gender prediction accuracy between female and male forms without impairing the translation quality.
Open AccessExploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation
We study the effect of tokenization on gender bias in machine translation, an aspect that has been largely overlooked in previous works. Specifically, we focus on the interactions between the frequency of gendered profession names in training data, their representation in the subword tokenizer's vocabulary, and gender bias. We observe that female and non-stereotypical gender inflections of profession names (e.g., Spanish "doctora" for "female doctor") tend to be split into multiple subword tokens. Our results indicate that the imbalance of gender forms in the model's training corpus is a major factor contributing to gender bias and has a greater impact than subword splitting. We show that analyzing subword splits provides good estimates of gender-form imbalance in the training data and can be used even when the corpus is not publicly available. We also demonstrate that fine-tuning just the token embedding layer can decrease the gap in gender prediction accuracy between female and male forms without impairing the translation quality.
- Open Access
- 19 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 111-120
The Perfect Victim
- 19 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 111-120
Open AccessThe Perfect Victim
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 885-896
Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation
Bar Iluz, Tomasz Limisiewicz, Gabriel Stanovsky, David Mareček. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 885-896
Open AccessExploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation
Bar Iluz, Tomasz Limisiewicz, Gabriel Stanovsky, David Mareček. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.