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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02381078
Contributor : Serena Villata <>
Submitted on : Wednesday, November 27, 2019 - 10:35:19 AM
Last modification on : Monday, December 2, 2019 - 9:59:02 AM

File

18298-78917-1-PB.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02381078, version 1

Collections

Citation

Johanna Frau, Milagro Teruel, Laura Alonso Alemany, Serena Villata. Different Flavors of Attention Networks for Argument Mining. Proceedings of the Thirty-Second International Florida Artificial Intelligence Research Society Conference, May 2019, Sarasota, United States. ⟨hal-02381078⟩

Share

Metrics

Record views

11

Files downloads

6