The LARGA (Learning Argumentation Axioms from Monological and Dialogical Texts) project aims at modeling and identifying rhetorical strategies in argumentation. LARGA is part of the 2nd phase of the RATIO (Robust Argumentation Machines) priority program, is funded by the DFG and runs from 2021 to 2024. The project is conducted in collaboration with Bauhaus University Weimar (PI: Benno Stein).
Most existing work on computational argumentation concentrates on argument mining and argumentation assessment, while the empirical knowledge about what arrangement strategies are effective for which text genre or mode as well as how to identify such kind of strategy knowledge is missing so far. We want to address this gap by introducing an axiomatic approach for modeling argument arrangement preferences on the basis of “topic-agnostic” attributes, which we have been compiling in the course of our recent research.
To this end, we ask the following questions:
- In what order should arguments be presented in a text?
- What rules or conventions guide these ordering decisions?
- In what way does a specific linearisation improve or diminish the acceptability of the author’s standpoint?
- Do principles exist that apply across text genres?
To answer these questions, we provide a concrete plan of how to acquire adequately annotated datasets and how to induce axioms i.e. argument arrangement patterns both in monological and dialogical settings, and to analyse interesting relations among these axioms. The resources developed as part of this project, including the annotations, code, axiomatic knowledge, and prototypical tools, will be made freely available, contributing to the RATIO priority program and research on argumentation in general.
Dr. Khalid Al-Khatib (University of Groningen)
René Knaebel (University of Potsdam)
Robin Schaefer (University of Potsdam)
Prof. Dr. Manfred Stede (University of Potsdam)
Prof. Dr. Benno Stein (Bauhaus University Weimar)
LARGA runs from 2021 to 2024.
- Robin Schaefer, René Knaebel, and Manfred Stede. On Selecting Training Corpora for Cross-Domain Claim Detection. In Proceedings of the 9th Workshop on Argument Mining (COLING), 181–186. Online and in Gyeongju, Republic of Korea, 2022. International Conference on Computational Linguistics. [Bibtex] [PDF]