Neural-Symbolic Argumentation Mining: An Argument in Favor of Deep Learning and Reasoning

Galassi, Andrea; Kersting, Kristian; Lippi, Marco; Shao, Xiaoting; Torroni, Paolo

doi:10.3389/fdata.2019.00052

Cited by 13 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…query answering). Examples include the neuro-symbolic concept learner and deepProbLog [Manhaeve et al, 2018;Galassi et al, 2020].…”

Section: Neural-symbolic Computing Taxonomymentioning

confidence: 99%

“…Furthermore, graph representations have useful properties such as permutation invariance and flexibility for generalization over the input size (models in the graph neural network family can be fed with graphs regardless of their size in terms of number of vertices). Graph convolutions can be seen as a variation of the well-known attention mechanism [Garcia and Bruna, 2018]. A graph convolution is essentially an attention layer with two key differences:…”

Section: Convolutions As Self-attentionmentioning

confidence: 99%

See 1 more Smart Citation

Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective

Lamb

Garcez

Gori

et al. 2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Neural-symbolic computing has now become the subject of interest of both academic and industry research laboratories. Graph Neural Networks (GNNs) have been widely used in relational and symbolic domains, with widespread application of GNNs in combinatorial optimization, constraint satisfaction, relational reasoning and other scientific domains. The need for improved explainability, interpretability and trust of AI systems in general demands principled methodologies, as suggested by neural-symbolic computing. In this paper, we review the state-of-the-art on the use of GNNs as a model of neural-symbolic computing. This includes the application of GNNs in several domains as well as their relationship to current developments in neural-symbolic computing.

show abstract

“…query answering). Examples include the neuro-symbolic concept learner and deepProbLog [Manhaeve et al, 2018;Galassi et al, 2020].…”

Section: Neural-symbolic Computing Taxonomymentioning

confidence: 99%

Section: Convolutions As Self-attentionmentioning

confidence: 99%

Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective

Lamb

Garcez

Gori

et al. 2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Therefore, if a neural network is trained to classify argument components, and another one is trained to detect links between them, additional global constraints can be enforced to adjust the weights of the networks toward admissible solutions. We refer to [10] for implementation examples with DeepProbLog and with GS-MLNs. Sum-Product Logic [35] even features deep hi- Here, the gating weights, possibly also leaf nodes, are parameterized by the output of neural networks given X.…”

Section: A Novel Tractable Deep Probabilistic Classifiermentioning

confidence: 99%

“…Only recently, a few works have taken some steps towards the integration of such methods, by applying techniques combining sub-symbolic classifiers with knowledge expressed in the form of rules and constraints to argumentation mining, see e.g. [10]. Moreover, argumentation-based machine learning employs computational models of argumentation for reasoning within machine learning itself [23,28,39].…”

Section: Introductionmentioning

confidence: 99%

Towards Understanding and Arguing with Classifiers: Recent Progress

et al. 2020

Self Cite

View full text Add to dashboard Cite

Machine learning and argumentation can potentially greatly benefit from each other. Combining deep classifiers with knowledge expressed in the form of rules and constraints allows one to leverage different forms of abstractions within argumentation mining. Argumentation for machine learning can yield argumentation-based learning methods where the machine and the user argue about the learned model with the common goal of providing results of maximum utility to the user. Unfortunately, both directions are currently rather challenging. For instance, combining deep neural models with logic typically only yields deterministic results, while combining probabilistic models with logic often results in intractable inference. Therefore, we review a novel deep but tractable model for conditional probability distributions that can harness the expressive power of universal function approximators such as neural networks while still maintaining a wide range of tractable inference routines. While this new model has shown appealing performance in classification tasks, humans cannot easily understand the reasons for its decision. Therefore, we also review our recent efforts on how to "argue" with deep models. On synthetic and real data we illustrate how "arguing" with a deep model about its explanations can actually help to revise the model, if it is right for the wrong reasons.

show abstract

“…C OMPLEX reasoning aims to comprehend and analyze the given information, and apply complex rules to draw correct inference [1,2]. As an essential ability for complex problem solving, it provides tremendous opportunities for many real-world scenarios, such as mathematical word problems, negotiation and argument, and medical diagnosis [3,4,5,6]. In recent years, having a computer pass admission examinations is a hot AI challenge towards complex reasoning, which offers an objective and accurate measurement with a certain difficulty.…”

Section: Introductionmentioning

confidence: 99%

From LSAT: The Progress and Challenges of Complex Reasoning

Wang¹,

Liu²,

Zhong³

et al. 2021

Preprint

View full text Add to dashboard Cite

Complex reasoning aims to draw a correct inference based on complex rules. As a hallmark of human intelligence, it involves a degree of explicit reading comprehension, interpretation of logical knowledge and complex rule application. In this paper, we take a step forward in complex reasoning by systematically studying the three challenging and domain-general tasks of the Law School Admission Test (LSAT), including analytical reasoning, logical reasoning and reading comprehension. We propose a hybrid reasoning system to integrate these three tasks and achieve impressive overall performance on the LSAT tests. The experimental results demonstrate that our system endows itself a certain complex reasoning ability, especially the fundamental reading comprehension and challenging logical reasoning capacities. Further analysis also shows the effectiveness of combining the pre-trained models with the task-specific reasoning module, and integrating symbolic knowledge into discrete interpretable reasoning steps in complex reasoning. We further shed a light on the potential future directions, like unsupervised symbolic knowledge extraction, model interpretability, few-shot learning and comprehensive benchmark for complex reasoning.

show abstract

Neural-Symbolic Argumentation Mining: An Argument in Favor of Deep Learning and Reasoning

Cited by 13 publications

References 43 publications

Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective

Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective

Towards Understanding and Arguing with Classifiers: Recent Progress

From LSAT: The Progress and Challenges of Complex Reasoning

Contact Info

Product

Resources

About