A Dataset Independent Set of Baselines for Relation Prediction in Argument Mining
This work addresses a key bottleneck for the Argument Mining community by providing standardized baselines to enable more effective comparison of methods, though it is incremental as it builds on existing datasets and tasks.
The authors tackled the problem of lacking a single relation prediction method that works across multiple argument mining datasets by proposing a set of dataset-independent neural baselines that achieve homogeneous results on all existing datasets for argumentative relation prediction.
Argument Mining is the research area which aims at extracting argument components and predicting argumentative relations (i.e.,support and attack) from text. In particular, numerous approaches have been proposed in the literature to predict the relations holding between the arguments, and application-specific annotated resources were built for this purpose. Despite the fact that these resources have been created to experiment on the same task, the definition of a single relation prediction method to be successfully applied to a significant portion of these datasets is an open research problem in Argument Mining. This means that none of the methods proposed in the literature can be easily ported from one resource to another. In this paper, we address this problem by proposing a set of dataset independent strong neural baselines which obtain homogeneous results on all the datasets proposed in the literature for the argumentative relation prediction task. Thus, our baselines can be employed by the Argument Mining community to compare more effectively how well a method performs on the argumentative relation prediction task.