Abstract
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.
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.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics |
| Number of pages | 7 |
| Place of Publication | Melbourne |
| Publisher | Association for Computational Linguistics |
| Publication date | 2018 |
| Publication status | Published - 2018 |
Keywords
- Gender prediction
- Cross-lingual embeddings
- Text bleaching
- Human prediction
- Lexical features