End-to-End Argument Mining as Augmented Natural Language Generation

Anonymous

Abstract: Argument Mining (AM) is a crucial aspect of computational argumentation, which deals with the identification and extraction of Argumentative Components (ACs) and their corresponding Argumentative Relations (ARs). This work proposes a unified end-to-end framework based on a generative paradigm, in which the argumentative structures are framed into label-augmented text, called Augmented Natural Language (ANL). Additionally, we explore the role of different types of markers in solving AM tasks. Through different marker-based fine-tuning strategies, we present an extensive study by integrating marker knowledge into our generative model. The proposed framework achieves competitive results to the state-of-the-art (SoTA) model and outperforms several baselines.

Paper Type: long

Research Area: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Contribution Types: NLP engineering experiment

Languages Studied: English