DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models
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.
Code (1)
Tasks
Argument MiningLogical Reasoning Reading ComprehensionSemantic ParsingvalidMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DeepATLAS: One-Shot Localization for Biomedical Data
This paper introduces the DeepATLAS foundational model for localization tasks in the domain of high-dimensional biomedical data. Upon convergence of the proposed self-supervised objective, a pretrained model maps an inpu…
One-Shot SegmentationDeepABM: Scalable, efficient and differentiable agent-based simulations via graph neural networks
We introduce DeepABM, a framework for agent-based modeling that leverages geometric message passing of graph neural networks for simulating action and interactions over large agent populations. Using DeepABM allows scali…
GPUModular Semantics and Characteristics for Bipolar Weighted Argumentation Graphs
This paper addresses the semantics of weighted argumentation graphs that are bipolar, i.e. contain both attacks and supports for arguments. It builds on previous work by Amgoud, Ben-Naim et. al. We study the various char…
AllModel-Agnostic Reachability Analysis on Deep Neural Networks
Verification plays an essential role in the formal analysis of safety-critical systems. Most current verification methods have specific requirements when working on Deep Neural Networks (DNNs). They either target one par…
modelThe DeepCAR Method: Forecasting Time-Series Data That Have Change Points
Many methods for time-series forecasting are known in classical statistics, such as autoregression, moving averages, and exponential smoothing. The DeepAR framework is a novel, recent approach for time-series forecasting…
Time SeriesTime Series AnalysisTime Series Forecasting