Open Access Repository

Neural-symbolic probabilistic argumentation machines

Riveret, R, Tran, S ORCID: 0000-0002-5912-293X and d'Avila Garcez, A 2020 , 'Neural-symbolic probabilistic argumentation machines', paper presented at the 17th International Conference Principles of Knowledge Representation and Reasoning, 12-18 September 2020, Rhodes, Greece.

140695 - Neural...pdf | Download (577kB)

| Preview


Neural-symbolic systems combine the strengths of neural networks and symbolic formalisms. In this paper, we introduce a neural-symbolic system which combines restricted Boltzmann machines and probabilistic semi-abstract argumentation. We propose to train networks on argument labellings explaining the data, so that any sampled data outcome is associated with an argument labelling. Argument labellings are integrated as constraints within restricted Boltzmann machines, so that the neural networks are used to learn probabilistic dependencies amongst argument labels. Given a dataset and an argumentation graph as prior knowledge, for every example/case K in the dataset, we use a so-called K- maxconsistent labelling of the graph, and an explanation of case K refers to a K-maxconsistent labelling of the given argumentation graph. The abilities of the proposed system to predict correct labellings were evaluated and compared with standard machine learning techniques. Experiments revealed that such argumentation Boltzmann machines can outperform other classification models, especially in noisy settings.

Item Type: Conference or Workshop Item (Paper)
Authors/Creators:Riveret, R and Tran, S and d'Avila Garcez, A
Keywords: neural-symbolic, argumentation, machine learning, reasoning
Journal or Publication Title: Proceedings of the 17th International Conference Principles of Knowledge Representation and Reasoning
DOI / ID Number:
Copyright Information:

Copyright 2020 2020 International Joint Conferences on Artificial Intelligence Organization

Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page