DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models

TL;DR

DeepA2 introduces a modular framework leveraging pre-trained language models like T5 for deep argument analysis, capable of reconstructing and formalizing arguments from texts, with promising results on synthetic and real datasets.

Contribution

The paper presents a novel modular framework, DeepA2, utilizing pre-trained models for comprehensive argument reconstruction and analysis, including a new synthetic dataset and evaluation on existing benchmarks.

Findings

Framework effectively reconstructs arguments with missing components.

Modular design emulates established argumentative heuristics.

Model handles multiple valid solutions and uncertainty.

Abstract

In this paper, we present and implement a multi-dimensional, modular framework for performing deep argument analysis (DeepA2) using current pre-trained language models (PTLMs). ArgumentAnalyst -- a T5 model (Raffel et al. 2020) set up and trained within DeepA2 -- reconstructs argumentative texts, which advance an informal argumentation, as valid arguments: It inserts, e.g., missing premises and conclusions, formalizes inferences, and coherently links the logical reconstruction to the source text. We create a synthetic corpus for deep argument analysis, and evaluate ArgumentAnalyst on this new dataset as well as on existing data, specifically EntailmentBank (Dalvi et al. 2021). Our empirical findings vindicate the overall framework and highlight the advantages of a modular design, in particular its ability to emulate established heuristics (such as hermeneutic cycles), to explore the model's uncertainty, to cope with the plurality of correct solutions (underdetermination), and to exploit higher-order evidence.