This paper extends the conformal prediction framework to rule extraction, making it possible to extract interpretable models from opaque models in a setting where either the infidelity or the error rate is bounded by a predefined significance level. Experimental results on 27 publicly available data sets show that all three setups evaluated produced valid and rather efficient conformal predicto...

Hybrid intelligent systems that combine knowledge based and artiicial neural network systems typically have four phases involving domain knowledge representation, mapping into connectionist network, network training, and rule extraction respectively. The nal phase is important because it can provide a trained connectionist architecture with explanation power and validate its output decisions. M...

Translation rule extraction is a fundamental problem in machine translation, especially for linguistically syntax-based systems that need parse trees from either or both sides of the bitext. The current dominant practice only uses 1-best trees, which adversely affects the rule set quality due to parsing errors. So we propose a novel approach which extracts rules from a packed forest that compac...

In this paper, we present concise but robust rules for dependency-based logical form identification with high accuracy. We describe our approach from an intuitive and formalized perspective, which we believe overcomes much of the complexity. In comparison to previous work, we believe ours is more compact and involves less rules and exceptions. We also provide the reader with a comparison of the...

The artificial neural networks (ANNs) are well suitable to solve a variety class of problems in a knowledge discovery field (e.g., in natural language processing) because the trained networks are more accurate at classifying the examples that represent a problem domain. However, the neural networks that consist of large number of weighted connections (called also links) and activation units oft...

Knowledge acquisition is, needless to say, important, because it is a key to the solution to one of the bottlenecks in artificial intelligence. Recently, knowledge acquisition using neural networks, called rule extraction, is attracting wide attention because of its computational simplicity and ability to generalize. Proposed in this paper is a novel approach to rule extraction named successive...

The application of knowledge extraction methodologies in support of medical informatics promises interesting developments that could potentially improve many aspects of healthcare services. In this paper we outline a multi-stage rule extraction pipeline for rule-based knowledge discovery. The featured methodology would facilitate operationally straightforward extraction of symbolic rules from m...