2023
Sociocultural knowledge is needed for selection of shots in hate speech detection tasks. Antonis Maronikolakis, Abdullatif Köksal, Hinrich Schütze. Pre-print
2022
Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments. Antonis Maronikolakis, Axel Wisiorek, Leah Nann, Haris Jabbar, Sahana Udupa and Hinrich Schütze. 2022. In Findings of the Association for Computational Linguistics: ACL 2022.
Analyzing Hate Speech Data along Racial, Gender and Intersectional Axes. Antonis Maronikolakis, Philip Baader, Hinrich Schütze. 2022. In Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing, NAACL.
Separating Hate Speech and Offensive Language Classes via Adversarial Debiasing. Shuzhou Yuan, Antonis Maronikolakis, Hinrich Schütze. 2022. In Proceedings of The 6th Workshop on Online Abuse and Harms, NAACL.
Ethical Scaling for Content Moderation: Extreme Speech and the (In)Significance of Artificial Intelligence. Sahana Udupa, Antonis Maronikolakis, Hinrich Schütze, Axel Wisiorek. 2022. Shorenstein Center, Harvard University.
2021
Wine is Not v i n. – On the Compatibility of Tokenizations Across Languages. Antonis Maronikolakis, Philipp Dufter and Hinrich Schütze. 2021. In Findings of the 2021 Conference on Empirical Methods in Natural Language Processing.
BERT Cannot Align Characters. Antonis Maronikolakis, Philipp Dufter and Hinrich Schütze. 2021. In Proceedings of The Second Workshop on Insights from Negative Results, EMNLP.
Artificial Intelligence, Extreme Speech, and the Challenges of Online Content Moderation. Sahana Udupa, Elonnai Hickok, Antonis Maronikolakis, Hinrich Schuetze, Laura Csuka, Axel Wisiorek, Leah Nann. 2021. AI4Dignity Project. EU Commission Policy Brief.
Identifying Automatically Generated Headlines Using Transformers. Antonis Maronikolakis, Hinrich Schütze, and Mark Stevenson. 2021. In Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda, pages 1–6, Online. Association for Computational Linguistics.
Multidomain Pretrained Language Models for Green NLP. Antonis Maronikolakis and Hinrich Schütze. 2021. In Proceedings of the Second Workshop on Domain Adaptation for NLP, pages 1–8, Kyiv, Ukraine. Association for Computational Linguistics.
2020
Analyzing Political Parody in Social Media. Antonis Maronikolakis, Danae Sánchez Villegas, Daniel Preotiuc-Pietro, and Nikolaos Aletras. 2020. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.