Learning Phonotactics Using ILP

TL;DR

This paper explores using Inductive Logic Programming to learn Dutch phonotactic rules, demonstrating how prior domain knowledge enhances the quality of learned theories and comparing different approaches.

Contribution

It introduces and compares two ILP-based methods for learning phonotactics, highlighting the importance of background knowledge in the learning process.

Findings

ILP effectively learns Dutch phonotactic rules

Quality of background knowledge impacts theory accuracy

Comparison shows different approaches vary in performance

Abstract

This paper describes experiments on learning Dutch phonotactic rules using Inductive Logic Programming, a machine learning discipline based on inductive logical operators. Two different ways of approaching the problem are experimented with, and compared against each other as well as with related work on the task. The results show a direct correspondence between the quality and informedness of the background knowledge and the constructed theory, demonstrating the ability of ILP to take good advantage of the prior domain knowledge available. Further research is outlined.