Neural networks learn to construct argumentation structures that explain classifications through support and attack relations, trained jointly with differentiable semantics and structure constraints.
Interpreting neural networks as quantitative argumentation frameworks.Proceed- ings of the AAAI Conference on Artificial Intelligence, 35(7):6463–6470, May 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep Arguing
Neural networks learn to construct argumentation structures that explain classifications through support and attack relations, trained jointly with differentiable semantics and structure constraints.