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

Gregor Betz, Kyle Richardson


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.
Anthology ID:
2022.starsem-1.2
Volume:
Proceedings of the 11th Joint Conference on Lexical and Computational Semantics
Month:
July
Year:
2022
Address:
Seattle, Washington
Venue:
*SEM
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
12–27
Language:
URL:
https://aclanthology.org/2022.starsem-1.2
DOI:
10.18653/v1/2022.starsem-1.2
Bibkey:
Cite (ACL):
Gregor Betz and Kyle Richardson. 2022. DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models. In Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, pages 12–27, Seattle, Washington. Association for Computational Linguistics.
Cite (Informal):
DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models (Betz & Richardson, *SEM 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/starsem-semeval-split/2022.starsem-1.2.pdf
Code
 vamsi995/paraphrase-generator
Data
AAACEntailmentBank