Using a Machine Learning Approach for Building Natural Language Interfaces for Databases: Application of Advanced Techniques in Inductive Logic Programming

Building a natural language interface for a database has been an interesting task since the 70‟s, which often requires creating a semantic parser. A study on using an advanced inductive logic programming (ILP) approach for semantic parser induction that combines different ILP learners to learn rules for ambiguity resolution is presented. Accuracy of the resulting induced semantic parser can be significantly improved due to the learning of more descriptive rules than those of each individual ILP learner. The task of learning semantic parsers in two different real world domains was attempted and results demonstrated that such an approach is promising.