Bleaching Text: Abstract Features for Cross-lingual Gender Prediction
Rob van der Goot, Nikola Ljubešić, Ian Matroos, Malvina Nissim, Barbara Plank · 2018
Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platformdependent.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.