Exploring Portuguese Hate Speech Detection in Low-Resource Settings: Lightly Tuning Encoder Models or In-Context Learning of Large Models?

This repository contains the code and results of PROPOR 2024 paper that compared in-context learning with two LLM chatbots and lightly tuning smaller encoder models.

---

CITING

Gabriel Assis, Annie Amorim, Jonnatahn Carvalho, Daniel de Oliveira, Daniela Vianna, and Aline Paes. 2024. Exploring Portuguese Hate Speech Detection in Low-Resource Settings: Lightly Tuning Encoder Models or In-Context Learning of Large Models?. In Proceedings of the 16th International Conference on Computational Processing of Portuguese, pages 301–311, Santiago de Compostela, Galicia/Spain. Association for Computational Lingustics.

BIBTEX

@inproceedings{assis-etal-2024-exploring, title = "Exploring {P}ortuguese {H}ate {S}peech {D}etection in {L}ow-{R}esource {S}ettings: {L}ightly {T}uning {E}ncoder {M}odels or {I}n-{C}ontext {L}earning of {L}arge {M}odels?", author = "Assis, Gabriel and Amorim, Annie and Carvalho, Jonnathan and de Oliveira, Daniel and Vianna, Daniela and Paes, Aline", editor = "Gamallo, Pablo and Claro, Daniela and Teixeira, Ant{\'o}nio and Real, Livy and Garcia, Marcos and Oliveira, Hugo Gon{\c{c}}alo and Amaro, Raquel", booktitle = "Proceedings of the 16th International Conference on Computational Processing of Portuguese", month = mar, year = "2024", address = "Santiago de Compostela, Galicia/Spain", publisher = "Association for Computational Lingustics", url = "https://aclanthology.org/2024.propor-1.31", pages = "301--311" }

FUNDING

This research was financed by CNPq (National Council for Scientific and Technological Development), grants 311275/2020-6 and 315750/2021-9, FAPERJ - Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro, process SEI-260003/000614/2023, and Coordenação de Aperfeiçoamento de Pessoal de Nível Superior – Brasil (CAPES) – Finance Code 001.