Different Flavors of Attention Networks for Argument Mining - Archive ouverte HAL Access content directly
Conference Papers Year :

Different Flavors of Attention Networks for Argument Mining

Abstract

Argument mining is a rising area of Natural Language Processing (NLP) concerned with the automatic recognition and interpretation of argument components and their relations. Neural models are by now mature technologies to be exploited for automating the argument mining tasks, despite the issue of data sparseness. This could ease much of the manual effort involved in these tasks, taking into account heterogeneous types of texts and topics. In this work, we evaluate different attention mechanisms applied over a state-of-the-art architecture for sequence labeling. We assess the impact of different flavors of attention in the task of argument component detection over two datasets: essays and legal domain. We show that attention not only models the problem better but also supports interpretability.
Fichier principal
Vignette du fichier
18298-78917-1-PB.pdf (1.29 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02381078 , version 1 (27-11-2019)

Identifiers

  • HAL Id : hal-02381078 , version 1

Cite

Johanna Frau, Milagro Teruel, Laura Alonso Alemany, Serena Villata. Different Flavors of Attention Networks for Argument Mining. FLAIRS 2019 - 32th International Florida Artificial Intelligence Research Society Conference, May 2019, Sarasota, United States. ⟨hal-02381078⟩
86 View
42 Download

Share

Gmail Facebook Twitter LinkedIn More