Bleaching Text: Abstract Features for Cross-lingual Gender Prediction

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

    Research output: Contribution to conferencePaperAcademic


    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.
    Original languageEnglish
    Number of pages7
    Publication statusPublished - Jul-2018
    Event56th Annual Meeting of the Association for Computational Linguistics - Melbourne Convention and Exhibition Centre, Melbourne, Australia
    Duration: 16-Jul-201820-Jul-2018


    Conference56th Annual Meeting of the Association for Computational Linguistics
    Abbreviated titleACL 2018
    Internet address

    Cite this