Towards bridging the neuro-symbolic gap: deep deductive reasoners

Ebrahimi, Monireh; Eberhart, Aaron; Bianchi, Federico; Hitzler, Pascal

doi:10.1007/s10489-020-02165-6

Cited by 24 publications

(25 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An example for a currently emerging line of research compatible with the thoughts just laid out, is that of so-called deep deductive reasoners [57], which are deep learning systems trained to perform deductive reasoning over formal logics. The deductive reasoning task can be framed as classification (a statement is or is not a logical consequence of a given theory) or as regression (produce all logical consequences under some finiteness constraints).…”

Section: Paths Forwardmentioning

confidence: 99%

Neuro-Symbolic Artificial Intelligence: Current Trends

Zhang¹,

Eberhart²,

Hitzler³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Paths Forwardmentioning

confidence: 99%

Neuro-Symbolic Artificial Intelligence: Current Trends

Zhang¹,

Eberhart²,

Hitzler³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…From the point of view of evaluating a neuro-symbolic reasoning procedure, the key aspects [22], in addition to the previously discussed conventional reasoning evaluation measures, are as follows.…”

Section: Conventional Reasoning Methodsmentioning

confidence: 99%

Neuro-Symbolic Techniques for Description Logic Reasoning (Student Abstract)

Singh

Mondal²,

Bhatia

et al. 2021

AAAI

View full text Add to dashboard Cite

With the goal to find scalable reasoning approaches, neuro-symbolic techniques have gained significant attention. However, the existing approaches do not take into account the inference capabilities of ontology languages that are based on expressive description logic (such as OWL 2). To fill this gap, we propose two approaches: an ontology-based embedding model for theories in EL++ description logic and a reinforcement learning-based solution for efficient tableau-based reasoning on description logic. We describe promising initial results of our efforts towards these directions and lay down the direction for future work.

show abstract

“…In the early days, the research on construction language mainly focused on its concept and theoretical connotation. For example, Ebrahimi et al used construction grammar theory to examine their research's linguistic and constructional meanings [9]. Kekki and Ivaska explored the relationship between constructional structure and its syntactic representation [10].…”

Section: Related Workmentioning

confidence: 99%

Exploring the Application of the Random Matrix Thinking Model in Teaching English Predicate Constructions

Liu

Wen

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

This paper, the random matrix thinking model, studies the grammatical features of verbs on random matrix and logical relations and designs a model for teaching English predicate constructions by combining random matrix thinking and arithmetic rules. In this paper, an attention mechanism-based English predicate verb recognition method and a BERT-based English predicate verb recognition method are proposed for the characteristics of predicate verbs as the focal point of sentences. Since the attention mechanism can obtain the long-distance semantic dependency information in the sentence, the attention mechanism-based method can effectively improve the recognition performance of the predicate verb compared with the traditional way. The BERT-based English predicative verb recognition model improves the former approach by taking full advantage of the input corpus and improving the model performance. A random matrix-based predicate verb uniqueness discrimination method is proposed for the uniqueness of predicate verbs in sentences. By setting the classification fitting conditions, the data can be optimized to output and fully fit the global identity of the predicate verb in the penalty during the training process, and better results are achieved.

show abstract

Towards bridging the neuro-symbolic gap: deep deductive reasoners

Cited by 24 publications

References 36 publications

Neuro-Symbolic Artificial Intelligence: Current Trends

Neuro-Symbolic Artificial Intelligence: Current Trends

Neuro-Symbolic Techniques for Description Logic Reasoning (Student Abstract)

Exploring the Application of the Random Matrix Thinking Model in Teaching English Predicate Constructions

Contact Info

Product

Resources

About