Logic-Based Learning of Answer Set Programs

Law, Mark; Russo, Alessandra; Broda, Krysia

doi:10.1007/978-3-030-31423-1_6

Cited by 15 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Sudoku grid validity datasets were generated using valid 4x4 and 9x9 Sudoku starting configurations obtained from Hanssen's Sudoku puzzle generator. 8 For the NN used in the 9x9 grids, we used digit classes 1-9 from the standard MNIST dataset [26] and created a training set of 54,078 examples and a test set of 9,021 examples. The MNIST test set was further split (∼70%/30%), maintaining an equal representation of digits, into two datasets as follows.…”

Section: E Dataset Details E1 Sudoku Grid Validitymentioning

confidence: 99%

See 1 more Smart Citation

FF-NSL: Feed-Forward Neural-Symbolic Learner

Cunnington¹,

Law²,

Russo³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Inductive Logic Programming (ILP) aims to learn generalised, interpretable hypotheses in a data-efficient manner. However, current ILP systems require training examples to be specified in a structured logical form. To address this problem, this paper proposes a neural-symbolic learning framework, called Feed-Forward Neural-Symbolic Learner (FF-NSL), that integrates state-of-the-art ILP systems, based on the Answer Set semantics, with Neural Networks (NNs), in order to learn interpretable hypotheses from labelled unstructured data. To demonstrate the generality and robustness of FF-NSL, we use two datasets subject to distributional shifts, for which pre-trained NNs may give incorrect predictions with high confidence. Experimental results show that FF-NSL outperforms tree-based and neural-based approaches by learning more accurate and interpretable hypotheses with fewer examples.

show abstract

Section: E Dataset Details E1 Sudoku Grid Validitymentioning

confidence: 99%

“…Learning from Answer Sets (LAS) [8] is a general ILP approach [6] supported by state-of-theart systems (ILASP [6] and FastLAS [7]) that are robust to noisy data [9] and, in the case of FastLAS, scalable to large hypothesis spaces [7]. The LAS approach learns logic programs expressed using Answer Set Programming (ASP) [10].…”

Section: Introductionmentioning

confidence: 99%

FF-NSL: Feed-Forward Neural-Symbolic Learner

Cunnington¹,

Law²,

Russo³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In previous works [1,2,3], a hybrid logic-based approach was proposed for ethical evaluation of chatbots' behavior, concerning online customer service chat points, w.r.t institution/company's codes of ethics and conduct. The approach is based on Answer Set Programming (ASP) as a knowledge representation and reasoning language [5], and Inductive Logic Programming (ILP) for learning ASP rules needed for ethical evaluation and reasoning [7]. The potential of logic-based approaches for programming machine ethics was discussed in [4] In this paper, we focus on the challenge of monitoring and evaluating the ethical behavior of dialogue systems by proposing and implementing an application for monitoring and evaluation of chatting agents' (human/artificial) ethical behavior in an online customer service chat point w.r.t their institution/company's codes of ethics and conduct.…”

Section: Introductionmentioning

confidence: 99%

A Logic-based Multi-agent System for Ethical Monitoring and Evaluation of Dialogues

Dyoub

Letteri

Lisi

2021

Electron. Proc. Theor. Comput. Sci.

View full text Add to dashboard Cite

Dialogue Systems are tools designed for various practical purposes concerning human-machine interaction. These systems should be built on ethical foundations because their behavior may heavily influence a user (think especially about children). The primary objective of this paper is to present the architecture and prototype implementation of a Multi Agent System (MAS) designed for ethical monitoring and evaluation of a dialogue system. A prototype application, for monitoring and evaluation of chatting agents' (human/artificial) ethical behavior in an online customer service chat point w.r.t their institution/company's codes of ethics and conduct, is developed and presented. Future work and open issues with this research are discussed.

show abstract

“…ILP (Inductive Logic Programming) algorithms (cf. [47,38,28]) are a subclass of ML algorithms aimed at learning logic programs. ILP does not require huge amounts of training examples such as other (statistical) Machine Learning methods and produces interpretable results, that means a set of rules which can be analyzed and adjusted if necessary.…”

Section: Introductionmentioning

confidence: 99%

Logic Programming and Machine Ethics

Dyoub

Lisi

2020

Electron. Proc. Theor. Comput. Sci.

View full text Add to dashboard Cite

Transparency is a key requirement for ethical machines. Verified ethical behavior is not enough to establish justified trust in autonomous intelligent agents: it needs to be supported by the ability to explain decisions. Logic Programming (LP) has a great potential for developing such perspective ethical systems, as in fact logic rules are easily comprehensible by humans. Furthermore, LP is able to model causality, which is crucial for ethical decision making.

show abstract

Logic-Based Learning of Answer Set Programs

Cited by 15 publications

References 29 publications

FF-NSL: Feed-Forward Neural-Symbolic Learner

FF-NSL: Feed-Forward Neural-Symbolic Learner

A Logic-based Multi-agent System for Ethical Monitoring and Evaluation of Dialogues

Logic Programming and Machine Ethics

Contact Info

Product

Resources

About