Skip to Main content Skip to Navigation
New interface
Conference papers

Hybrid Emoji-Based Masked Language Models for Zero-Shot Abusive Language Detection

Michele Corazza 1 Stefano Menini 2 Elena Cabrio 3 Sara Tonelli 2 Serena Villata 3 
3 WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics
CRISAM - Inria Sophia Antipolis - Méditerranée , Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
Abstract : Recent studies have demonstrated the effectiveness of cross-lingual language model pre-training on different NLP tasks, such as natural language inference and machine translation. In our work, we test this approach on social media data, which are particularly challenging to process within this framework, since the limited length of the textual messages and the irregularity of the language make it harder to learn meaningful encodings. More specifically, we propose a hybrid emoji-based Masked Language Model (MLM) to leverage the common information conveyed by emo-jis across different languages and improve the learned cross-lingual representation of short text messages, with the goal to perform zero-shot abusive language detection. We compare the results obtained with the original MLM to the ones obtained by our method, showing improved performance on German, Italian and Spanish.
Complete list of metadata

Cited literature [40 references]  Display  Hide  Download
Contributor : Serena Villata Connect in order to contact the contributor
Submitted on : Tuesday, October 20, 2020 - 11:28:47 AM
Last modification on : Tuesday, October 25, 2022 - 4:18:32 PM
Long-term archiving on: : Thursday, January 21, 2021 - 6:50:47 PM


Files produced by the author(s)


  • HAL Id : hal-02972203, version 1


Michele Corazza, Stefano Menini, Elena Cabrio, Sara Tonelli, Serena Villata. Hybrid Emoji-Based Masked Language Models for Zero-Shot Abusive Language Detection. EMNLP 2020 - Conference on Empirical Methods in Natural Language Processing, Nov 2020, Virtual, France. ⟨hal-02972203⟩



Record views


Files downloads