Knowledge Unit Relation Recognition Based on Markov Logic Networks

Abstract

Knowledge unit (KU) is the smallest integral knowledge object in a given domain. Knowledge unit relation recognition is to discover implicit relations among KUs, which is a crucial problem in information extraction. This paper proposes a knowledge unit relation recognition framework based on Markov Logic Networks, which combines probabilistic graphical models and first-order logic by attaching a weight to each first-order formula. The framework is composed principally of structure learning, artificial add or delete formulas, weight learning and inferring. According to the semantic analysis of KUs and their relations, ground predicate set is first extracted. Next, the ground predicate set is inputted into structure learning module to achieve weight formula set. Then, in order to overcome limitations of structure learning, the weight rule set is added or deleted by human. The new weight formula set is turned into weight learning module to acquire the last weight formula set. Finally, knowledge unit relations are recognized by inferring module with the last weight formula set. Experiments on the four data sets related to computer domain show the utility of this approach. The time complexity of structure learning is also analyzed