Preventing author profiling through zero-shot multilingual back-translation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

Preventing author profiling through zero-shot multilingual back-translation

David Ifeoluwa Adelani
  • Function : Author
  • PersonId : 1073845
Miaoran Zhang
  • Function : Author
  • PersonId : 1110825
Xiaoyu Shen
  • Function : Author
  • PersonId : 1110826
Ali Davody
  • Function : Author
  • PersonId : 1073846
Thomas Kleinbauer
  • Function : Author
  • PersonId : 1073842
Dietrich Klakow
  • Function : Author
  • PersonId : 1095147


Documents as short as a single sentence may inadvertently reveal sensitive information about their authors, including e.g. their gender or ethnicity. Style transfer is an effective way of transforming texts in order to remove any information that enables author profiling. However, for a number of current state-of-theart approaches the improved privacy is accompanied by an undesirable drop in the downstream utility of the transformed data. In this paper, we propose a simple, zero-shot way to effectively lower the risk of author profiling through multilingual back-translation using off-the-shelf translation models. We compare our models with five representative text style transfer models on three datasets across different domains. Results from both an automatic and a human evaluation show that our approach achieves the best overall performance while requiring no training data. We are able to lower the adversarial prediction of gender and race by up to 22% while retaining 95% of the original utility on downstream tasks.
Fichier principal
Vignette du fichier
adelani_EMNLP2021.pdf (233.62 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03350906 , version 1 (21-09-2021)


  • HAL Id : hal-03350906 , version 1


David Ifeoluwa Adelani, Miaoran Zhang, Xiaoyu Shen, Ali Davody, Thomas Kleinbauer, et al.. Preventing author profiling through zero-shot multilingual back-translation. 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2021, Punta Cana, Dominica. ⟨hal-03350906⟩
37 View
63 Download


Gmail Facebook Twitter LinkedIn More