
Nicolás Benjamín Ocampo
- Université Côte d'Azur (UniCA)
- Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S)
- Centre National de la Recherche Scientifique (CNRS)
- Web-Instrumented Man-Machine Interactions, Communities and Semantics (WIMMICS)
Présentation
I am a third-year PhD student in Computer Science (CS) at Université Côte d’Azur, Inria, CNRS, I3S, and a member of the Wimmics Research Team working on Implicit and Subtle Abusive Language using Machine Learning and Natural Language Processing (NLP).
My current research interests lie in the intersection of linguistics and NLP. My thesis topic aims to properly represent implicit and subtle (instances with irony, sentiment, exaggeration, circumlocution, etc) for abusive language detection and downstream tasks. After a proper representation of these notions with the WIMMICS team we aim for generating counter-narratives automatically in order to provide an informative answer that counter-argues a message, giving more context to social media users.
Compétences
Publications
Publications
|
PEACE: Providing Explanations and Analysis for Combating Hate ExpressionsECAI 2024 - 27th European Conference on Artificial Intelligence, Oct 2024, Santiago de Compostela, Spain
Communication dans un congrès
hal-04684950
v1
|
|
Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech CounteringEMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Nov 2024, Miami (Florida), United States. ⟨10.48550/arXiv.2410.03466⟩
Communication dans un congrès
hal-04734455
v1
|
|
Unveiling the Hate: Generating Faithful and Plausible Explanations for Implicit and Subtle Hate Speech DetectionNLDB 2024 - 29th International Conference on Natural Language & Information Systems, Jun 2024, Torino, Italy
Communication dans un congrès
hal-04658110
v2
|
|
An In-depth Analysis of Implicit and Subtle Hate Speech MessagesEACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, May 2023, Dubrovnik, France. pp.1997-2013, ⟨10.18653/v1/2023.eacl-main.147⟩
Communication dans un congrès
hal-04214094
v2
|
|
Unmasking the Hidden Meaning: Bridging Implicit and Explicit Hate Speech Embedding RepresentationsEMNLP 2023 - Conference on Empirical Methods in Natural Language Processing, Dec 2023, Singapore, France. pp.6626-6637, ⟨10.18653/v1/2023.findings-emnlp.441⟩
Communication dans un congrès
hal-04351644
v2
|
|
Playing the Part of the Sharp Bully : Generating Adversarial Examples for Implicit Hate Speech DetectionACL 2023 - 61st Annual Meeting of the Association for Computational Linguistics, Jul 2023, Toronto, Canada. pp.2758-2772, ⟨10.18653/v1/2023.findings-acl.173⟩
Communication dans un congrès
hal-04214125
v1
|