Learning Inference Rules from Data
dc.contributor.author | Sakama, Chiaki | |
dc.contributor.author | Inoue, Katsumi | |
dc.contributor.author | Ribeiro, Tony | |
dc.date.accessioned | 2021-04-23T09:27:09Z | |
dc.date.available | 2021-04-23T09:27:09Z | |
dc.date.issued | 2019 | |
dc.description.abstract | This paper considers the possibility of designing AI that can learn logical or non-logical inference rules from data. We first provide an abstract framework for learning logics. In this framework, an agent $${{{\mathcal {A}}}}$$ A provides training examples that consist of formulas S and their logical consequences T . Then a machine $${{{\mathcal {M}}}}$$ M builds an axiomatic system that makes T a consequence of S . Alternatively, in the absence of an agent $$\mathcal{A}$$ A , a machine $${{{\mathcal {M}}}}$$ M seeks an unknown logic underlying given data. We next consider the problem of learning logical inference rules by induction. Given a set S of propositional formulas and their logical consequences T , the goal is to find deductive inference rules that produce T from S . We show that an induction algorithm LF1T , which learns logic programs from interpretation transitions, successfully produces deductive inference rules from input data. Finally, we consider the problem of learning non-logical inference rules. We address three case studies for learning abductive inference, frame axioms, and conversational implicature. Each case study uses machine learning techniques together with metalogic programming. | de |
dc.identifier.doi | 10.1007/s13218-019-00597-y | |
dc.identifier.pissn | 1610-1987 | |
dc.identifier.uri | http://dx.doi.org/10.1007/s13218-019-00597-y | |
dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/36240 | |
dc.publisher | Springer | |
dc.relation.ispartof | KI - Künstliche Intelligenz: Vol. 33, No. 3 | |
dc.relation.ispartofseries | KI - Künstliche Intelligenz | |
dc.subject | Induction | |
dc.subject | Inference rule | |
dc.subject | Machine learning | |
dc.title | Learning Inference Rules from Data | de |
dc.type | Text/Journal Article | |
gi.citation.endPage | 278 | |
gi.citation.startPage | 267 |