@conference{semantic-gsi-conference-2019,
author = "Benito-S{\'a}nchez, Diego and Araque, Oscar and Iglesias, Carlos A.",
abstract = "This paper describes the GSI-UPM system for SemEval-2019 Task 5, which tackles multilingual detection of hate speech on Twitter. The main contribution of the paper is the use of a method based on word embeddings and semantic similarity combined with traditional paradigms, such as n-grams, TF-IDF and POS. This combination of several features is fine-tuned through ablation tests, demonstrating the usefulness of different features. While our approach outperforms baseline classifiers on different sub-tasks, the best of our submitted runs reached the 5th position on the Spanish sub-task A.
",
address = "Minneapolis, USA",
booktitle = "Proceedings of SemEval 2019",
keywords = "hate speech;twitter;word embedding",
month = "June",
title = "{S}emantic {S}imilarity and {W}ord {E}mbeddings for {M}ultilingual {D}etection of {H}ate {S}peech {A}gainst {I}mmigrants and {W}omen on {T}witter",
year = "2019",
}