@InProceedings{vandergoot-EtAl:2018:Short,
  author    = {van der Goot, Rob  and  Ljubešić, Nikola  and  Matroos, Ian  and  Nissim, Malvina  and  Plank, Barbara},
  title     = {Bleaching Text: Abstract Features for Cross-lingual Gender Prediction},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {383--389},
  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.},
  url       = {http://www.aclweb.org/anthology/P18-2061}
}