Neural-Symbolic Learning and Reasoning: A Survey and Interpretation

Besold, Tarek R.; Garcez, Artur d'Avila; Bader, Sebastian; Bowman, Howard; Domingos, Pedro; Hitzler, Pascal; Kuehnberger, Kai-Uwe; Lamb, Luis C.; Lowd, Daniel; Lima, Priscila Machado Vieira; de Penning, Leo; Pinkas, Gadi; Poon, Hoifung; Zaverucha, Gerson

doi:10.48550/arxiv.1711.03902

Cited by 31 publications

(40 citation statements)

References 104 publications

(150 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, neural models depend a lot on training data and are computationally expensive to train, and the performance will sharply decrease with limited data and resource. c) Neural-Symbolic Models: To combine the advantages and circumvent the shortcomings of both symbolic and neural methods, neural-symbolic models which integrate symbolic logic and neural representation are widely studied [69,70,71,72,73]. Some work employs a neural module to parse the language into executable programs [74,18] and deterministically executing the programs to find the answer in a symbolic module.…”

Section: B Advanced Methods Of Complex Reasoningmentioning

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

Section: B Advanced Methods Of Complex Reasoningmentioning

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

show abstract

“…Nevertheless, human reasoning is sensitive to contextual modeling, and methods of contextual modeling in AI have followed the field from logical-symbolic models of context ("good oldfashioned AI" or GOFAI) before the AI winter of the 1980s to probabilistic and deep-learned vector similarity in the 2010s. Recently, GOFAI methods have resurfaced in the increasingly machine learning-driven modern AI community as a method of reincorporating some of the structure they provide into the flexible representations provided by deep learning (e.g., Besold et al (2017); Garcez et al (2019); Mao et al (2019); Marcus & Davis (2019). 2 The question of better incorporating contextual structure into deep learning necessarily raises the question of the analytic and structural units of context.…”

Section: Multimodal Communication In Contextmentioning

confidence: 99%

Neurosymbolic AI for Situated Language Understanding

Krishnaswamy,

Pustejovsky

2020

Preprint

View full text Add to dashboard Cite

In recent years, data-intensive AI, particularly the domain of natural language processing and understanding, has seen significant progress driven by the advent of large datasets and deep neural networks that have sidelined more classic AI approaches to the field. These systems can apparently demonstrate sophisticated linguistic understanding or generation capabilities, but often fail to transfer their skills to situations they have not encountered before. We argue that computational situated grounding provides a solution to some of these learning challenges by creating situational representations that both serve as a formal model of the salient phenomena, and contain rich amounts of exploitable, task-appropriate data for training new, flexible computational models. Our model reincorporates some ideas of classic AI into a framework of neurosymbolic intelligence, using multimodal contextual modeling of interactive situations, events, and object properties. We discuss how situated grounding provides diverse data and multiple levels of modeling for a variety of AI learning challenges, including learning how to interact with object affordances, learning semantics for novel structures and configurations, and transferring such learned knowledge to new objects and situations.

show abstract

“…Neural-symbolic systems have been applied to various problems and successful applications include ontology learning, hardware/software specification, fault diagnosis, robotics, training and assessment in simulators (Hitzler et al, 2005;de Penning et al, 2011;Garcez et al, 2015;Besold et al, 2017). Recently, there are other research efforts which are in the topical proximity of the core field in neural-symbolic integration (Besold et al, 2017), including paradigms in computation and representation such as "conceptors" (Jaeger, 2014), "Neural Turing Machines" (NTMs) (Graves et al, 2014) and other application systems which are based on connectionist methods partially or fully but applied to tasks which conceptually operates on a symbolic level such as visual analogy-making (Reed et al, 2015) and Go-playing (Silver et al, 2016).…”

Section: Related Workmentioning

confidence: 99%

Generalize Symbolic Knowledge With Neural Rule Engine

Shen¹,

Xu²,

Lu³

2018

Preprint

View full text Add to dashboard Cite

Neural-symbolic learning aims to take the advantages of both neural networks and symbolic knowledge to build better intelligent systems. As neural networks have dominated the state-of-the-art results in a wide range of NLP tasks, it attracts considerable attention to improve the performance of neural models by integrating symbolic knowledge. Different from existing works, this paper investigates the combination of these two powerful paradigms from the knowledge-driven side. We propose Neural Rule Engine (NRE), which can learn knowledge explicitly from logic rules and then generalize them implicitly with neural networks. NRE is implemented with neural module networks in which each module represents an action of the logic rule. The experiments show that NRE could greatly improve the generalization abilities of logic rules with a significant increase on recall. Meanwhile, the precision is still maintained at a high level.

show abstract

Neural-Symbolic Learning and Reasoning: A Survey and Interpretation

Cited by 31 publications

References 104 publications

From LSAT: The Progress and Challenges of Complex Reasoning

From LSAT: The Progress and Challenges of Complex Reasoning

Neurosymbolic AI for Situated Language Understanding

Generalize Symbolic Knowledge With Neural Rule Engine

Contact Info

Product

Resources

About