Bleaching Text: Abstract Features for Cross-lingual Gender Prediction

Rob van der Goot, Nikola Ljubesi, Ian Matroos, Malvina Nissim, Barbara Plank

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review


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.
TitelProceedings of the 56th Annual Meeting of the Association for Computational Linguistics
Antal sider7
ForlagAssociation for Computational Linguistics
StatusUdgivet - 2018


Dyk ned i forskningsemnerne om 'Bleaching Text: Abstract Features for Cross-lingual Gender Prediction'. Sammen danner de et unikt fingeraftryk.