Argumentative Link Prediction using Residual Networks and Multi-Objective Learning

Publicly Accessible Resources

Abstract

We explore the use of residual networks for argumentation mining, with an emphasis on link prediction. We propose a domain-agnostic method that makes no assumptions on document or argument structure. We evaluate our method on a challenging dataset consisting of user-generated comments collected from an online platform. Results show that our model outperforms an equivalent deep network and offers results comparable with state-of-the-art methods that rely on domain knowledge.

 

Publication available at

http://aclweb.org/anthology/W18-5201

 

Cite as

Andrea Galassi, Marco Lippi, and Paolo Torroni. 2018. Argumentative link prediction using residual networks and multi-objective learning. In Proceedings of the 5th Workshop on Argument Mining, pages 1–10. Association for Computational Linguistics. URL: http://aclweb.org/anthology/W18-5201

 

Additional material

Presentation: Argumentative Link Prediction Using Residual Networks and Multi-Objective Learning