×

DeepA2

swMATH ID: 42471
Software Authors: Gregor Betz, Kyle Richardson
Description: 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.
Homepage: https://arxiv.org/abs/2110.01509
Dependencies: Python
Keywords: arXiv_cs.CL; Artificial Intelligence; arXiv_cs.AI; DeepA2; Python; PTLMs; T5 model
Related Software: Transformers; ProofWriter; multiPRover; RuleTaker; BLEURT; BERT; z3; Python
Referenced in: 0 Publications

Standard Articles

1 Publication describing the Software Year
DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models
Gregor Betz, Kyle Richardson
2022