Explaining Explanations in Probabilistic Logic Programming
The emergence of tools based on artificial intelligence has also led to the need of producing explanations which are understandable by a human being. In most approaches, the system is considered a black box, making it difficult to generate appropriate explanations. In this work, though, we consider a setting where models are transparent: probabilistic logic programming (PLP), a paradigm that combines logic programming for knowledge representation and probability to model uncertainty. However, given a query, the usual notion of explanation is associated with a set of choices, one for each random variable of the model. Unfortunately, such a set does not explain why the query is true and, in fact, it may contain choices that are actually irrelevant for the considered query. To improve this situation, we present in this paper an approach to explaining explanations which is based on defining a new query-driven inference mechanism for PLP where proofs are labeled with "choice expressions", a compact and easy to manipulate representation for sets of choices. The combination of proof trees and choice expressions allows us to produce comprehensible query justifications with a causal structure.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Probabilistic Sufficient Explanations
Understanding the behavior of learned classifiers is an important task, and various black-box explanations, logical reasoning approaches, and model-specific methods have been proposed. In this paper, we introduce probabi…
Logical ReasoningExplanations as Programs in Probabilistic Logic Programming
The generation of comprehensible explanations is an essential feature of modern artificial intelligence systems. In this work, we consider probabilistic logic programming, an extension of logic programming which can be u…
Formally Explaining Decision Tree Models with Answer Set Programming
Decision tree models, including random forests and gradient-boosted decision trees, are widely used in machine learning due to their high predictive performance. However, their complex structures often make them difficul…
Lazy Explanation-Based Approximation for Probabilistic Logic Programming
We introduce a lazy approach to the explanation-based approximation of probabilistic logic programs. It uses only the most significant part of the program when searching for explanations. The result is a fast and anytime…
Deep Probabilistic Programming Languages: A Qualitative Study
Deep probabilistic programming languages try to combine the advantages of deep learning with those of probabilistic programming languages. If successful, this would be a big step forward in machine learning and programmi…
BIG-bench Machine LearningProbabilistic Programming