Grammar learning using Inductive Logic Programming

Stephen Pulman, James Cussens

Research output: Contribution to journalArticle


This paper gives a brief introduction to a particular machine learning method known as inductive logic programming. It is argued that this method, unlike many current statistically based machine learning methods, implies a view of grammar learning that bears close affinity to the views linguists have of the logical problem of language acquisition, Two experiments in grammar learning using this technique are described, using a unification grammar formalism, and positive-only data.
Original languageEnglish
Pages (from-to)31-45
Number of pages15
JournalOxford University Working Papers in Linguistics, Philology and Phonetics
Publication statusPublished - 1 May 2001

Cite this