Header

UZH-Logo

Maintenance Infos

Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model


Amrhein, Chantal; Schottmann, Florian; Sennrich, Rico; Läubli, Samuel (2023). Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, Canada, 9 July 2023 - 14 July 2023. Association for Computational Linguistics, 4486-4506.

Abstract

Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more gender-fair language by creating pseudo training data through linguistic rules. However, this approach is not practical for languages with more complex morphology than English. We hypothesise that creating training data in the reverse direction, i.e. starting from gender-fair text, is easier for morphologically complex languages and show that it matches the performance of state-of-the-art rewriting models for English. To eliminate the rule-based nature of data creation, we instead propose using machine translation models to create gender-biased text from real gender-fair text via round-trip translation. Our approach allows us to train a rewriting model for German without the need for elaborate handcrafted rules. The outputs of this model increased gender-fairness as shown in a human evaluation study.

Abstract

Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more gender-fair language by creating pseudo training data through linguistic rules. However, this approach is not practical for languages with more complex morphology than English. We hypothesise that creating training data in the reverse direction, i.e. starting from gender-fair text, is easier for morphologically complex languages and show that it matches the performance of state-of-the-art rewriting models for English. To eliminate the rule-based nature of data creation, we instead propose using machine translation models to create gender-biased text from real gender-fair text via round-trip translation. Our approach allows us to train a rewriting model for German without the need for elaborate handcrafted rules. The outputs of this model increased gender-fairness as shown in a human evaluation study.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

1 download since deposited on 28 Jul 2023
1 download since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
06 Faculty of Arts > Zurich Center for Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:14 July 2023
Deposited On:28 Jul 2023 10:50
Last Modified:03 Jan 2024 15:03
Publisher:Association for Computational Linguistics
OA Status:Green
Publisher DOI:https://doi.org/10.18653/v1/2023.acl-long.246
  • Content: Published Version
  • Language: English
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)