We explore the use of residual networks and neural attention for multiple argument mining tasks. We propose a residual architecture that exploits attention, multi-task learning, and makes use of ensemble, without any assumption on document or argument structure. We present an extensive experimental evaluation on five different corpora of user-generated comments, scientific publications, and persuasive essays. Our results show that our approach is a strong competitor against state-of-the-art architectures with a higher computational footprint or corpus-specific design, representing an interesting compromise between generality, performance accuracy and reduced model size.

Multi-Task Attentive Residual Networks for Argument Mining

Andrea Galassi
Primo
;
Paolo Torroni
2023

Abstract

We explore the use of residual networks and neural attention for multiple argument mining tasks. We propose a residual architecture that exploits attention, multi-task learning, and makes use of ensemble, without any assumption on document or argument structure. We present an extensive experimental evaluation on five different corpora of user-generated comments, scientific publications, and persuasive essays. Our results show that our approach is a strong competitor against state-of-the-art architectures with a higher computational footprint or corpus-specific design, representing an interesting compromise between generality, performance accuracy and reduced model size.
2023
Andrea Galassi; Marco Lippi; Paolo Torroni
File in questo prodotto:
File Dimensione Formato  
2102.12227v1.pdf

accesso aperto

Descrizione: pre-print
Tipo: Preprint
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 2.8 MB
Formato Adobe PDF
2.8 MB Adobe PDF Visualizza/Apri
Multi-Task_Attentive_Residual_Networks_for_Argument_Mining.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 2.87 MB
Formato Adobe PDF
2.87 MB Adobe PDF Visualizza/Apri
Multi-Task-Attentive-Residual-Networks-for-Argument-Mining.pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 2.54 MB
Formato Adobe PDF
2.54 MB 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/11585/816442
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 0
social impact