Transfer Learning with Sentence Embeddings for Argumentative Evidence Classification

This work describes a simple Transfer Learning methodology aiming at discriminating evidences related to Argumentation Schemes using three different pre-trained neural architectures. Although Transfer Learning techniques are increasingly gaining momentum, the number of Transfer Learning works in the field of Argumentation Mining is relatively little and, to the best of our knowledge, no attempt has been performed towards the specific direction of discriminating evidences related to Argumentation Schemes. The research question of this paper is whether Transfer Learning can discriminate Argumentation Schemes’ components, a crucial yet rarely explored task in Argumentation Mining. Results show that, even with small amount of data, classifiers trained on sentence embeddings extracted from pre-trained transformers can achieve encouraging scores, outperforming previous results on evidence classification.