Bleaching Text: Abstract Features for Cross-lingual Gender Prediction
By Rob van der Goot, Nikola Ljubesic, Ian Matroos, Malvina Nissim, Barbara Plank. 2018
63 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Elizaveta Kuzmenko
- Marco Guerini
- Barbara Plank
- Serra Sinem Tekiroğlu
- Yi-Ling Chung
- Sebastian Ruder
- Anders Søgaard
- Isabelle Augenstein
Citations in the corpus
- CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech (2019, methodology): “…NLP can be used for several tasks, such as characterizing personal linguistic styles (Johannsen et al., 2015; Hovy and Spruit, 2016; van der Goot et al., 2018; DellOrletta and Nissim, 2018), improving text classification (Mandel et al., 2012; Volkova et al., 2013; Hovy, 2015), or…”
- Misogyny Detection in Twitter: a Multilingual and Cross-Domain Study (2020, unknown): “Basile and Rubagotti (2018) used the bleaching approach van der Goot, Ljubešić, Matroos, Nissim, and Plank (2018) to run cross-lingual experiments between Italian and English in the context of their participation to the AMI EVALITA 2018 Fersini et al. (2018a) evaluation campaign.”
- Predicting Authorship and Author Traits from Keystroke Dynamics (2018, background): “…a few (Mairesse and Walker, 2006; Luyckx and Daelemans, 2008; Rao et al., 2010; Rosenthal and McKeown, 2011; Nguyen et al., 2011; Volkova et al., 2013; Flekova et al., 2016b; Verhoeven et al., 2016; van Dalen et al., 2017; Ljubeˇsi´c et al., 2017; Emmery et al., 2017; van der Goot et al., 2018).”