This technical report illustrates the system developed by the CHILab team for the competition HaSpeeDe3 as part of the EVALITA 2023 campaign. The key idea for HaSpeeDe3 task A - Political Hate Speech Detection - Textual, was to develop different systems arranged as suitable combinations of the Pre-Trained Language Model (PTLM) used for embedding extraction, neural architectures for further elaborations over the embeddings and a classifier. In particular, dense layers, LSTM, BiLSTM and Transformers were used. The best performing system across the ones investigated in this report was made by embeddings extracted via XLM-RoBERTa coupled with BiLSTM that reaches a macro-F1 score of 0.876.

Siragusa I., Pirrone R. (2023). CHILab at HaSpeeDe3: Overview of the Taks A Textual. In M.M. Lai, M. Polignano, V. Russo, R. Sprugnoli, G. Venturi (a cura di), CEUR Workshop Proceedings. CEUR-WS.

CHILab at HaSpeeDe3: Overview of the Taks A Textual

Siragusa I.
Primo
;
Pirrone R.
Secondo
2023-09-02

Abstract

This technical report illustrates the system developed by the CHILab team for the competition HaSpeeDe3 as part of the EVALITA 2023 campaign. The key idea for HaSpeeDe3 task A - Political Hate Speech Detection - Textual, was to develop different systems arranged as suitable combinations of the Pre-Trained Language Model (PTLM) used for embedding extraction, neural architectures for further elaborations over the embeddings and a classifier. In particular, dense layers, LSTM, BiLSTM and Transformers were used. The best performing system across the ones investigated in this report was made by embeddings extracted via XLM-RoBERTa coupled with BiLSTM that reaches a macro-F1 score of 0.876.
2-set-2023
Siragusa I., Pirrone R. (2023). CHILab at HaSpeeDe3: Overview of the Taks A Textual. In M.M. Lai, M. Polignano, V. Russo, R. Sprugnoli, G. Venturi (a cura di), CEUR Workshop Proceedings. CEUR-WS.
File in questo prodotto:
File Dimensione Formato  
paper23.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Versione Editoriale
Dimensione 383.73 kB
Formato Adobe PDF
383.73 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10447/619235
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact