# Bleaching Text: Abstract Features for Cross-lingual Gender Prediction

arXiv: https://arxiv.org/abs/1805.03122 · HTML: https://mlsanity.com/paper/1805.03122/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2018.

## Built on by (most cited first, 6 of 6)

- [GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing](https://mlsanity.com/paper/2407.00600/) (2024)
- [A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models](https://mlsanity.com/paper/2402.13636/) (2024)
- [The Dark Side of the Language: Pre-trained Transformers in the DarkNet](https://mlsanity.com/paper/2201.05613/) (2022)
- [Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models](https://mlsanity.com/paper/2210.13029/) (2022)
- [Syllabic Quantity Patterns as Rhythmic Features for Latin Authorship Attribution](https://mlsanity.com/paper/2110.14203/) (2021)
- [Probing Omissions and Distortions in Transformer-based RDF-to-Text Models](https://mlsanity.com/paper/2409.16707/) (2024)

## Abstract (arXiv)

Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent. Cross-lingual embeddings circumvent some of these limitations, but capture gender-specific style less. We propose an alternative: bleaching text, i.e., transforming lexical strings into more abstract features. This study provides evidence that such features allow for better transfer across languages. Moreover, we present a first study on the ability of humans to perform cross-lingual gender prediction. We find that human predictive power proves similar to that of our bleached models, and both perform better than lexical models.