ILP techniques for free-text input processing

This paper presents an application of some Inductive logic programming (ILP) techniques for checking user's answer correctness in a Computer-Aided Language Learning (CALL) system STyLE (Scientific Terminology Learning Environment). STyLE supports adaptive learning of English terminology with a target user group of non-native English speakers. In STyLE are implemented many original features that make this system intelligent and adaptive, but we will focus only on one of them: supporting learner-system communication in Natural Language (NL). The proposed ILP system RICH is used for generation of least generalization(LG) and greatest specialization (G S) of the set of possible correct answers of a given-question to the user from the system. The user's answer is correct if it is between LG and GS of the correct answers' set.