Different Flavors of Attention Networks for Argument Mining.

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.