Inductive Logic Programming: Issues, Results and the Challenge of Learning Language in Logic

Inductive Logic Programming (ILP) is the area of AI which deals with the induction of hypothesised predicate deenitions from examples and background knowledge. Logic programs are used as a single representation for examples, background knowledge and hypotheses. ILP is diierentiated from most other forms of Machine Learning (ML) both by its use of an expressive representation language and its ability to make use of logically encoded background knowledge. This has allowed successful applications of ILP in areas such as molecular biology and natural language which both have rich sources of background knowledge and both beneet from the use of an expressive concept representation languages. For instance, the ILP system Progol has recently been used to generate comprehensible descriptions of the 23 most populated fold classes of proteins, where no such descriptions had previously been formulated manually. In the natural language area ILP has not only been shown to have higher accuracies than various other ML approaches in learning the past tense of English but also shown to be capable of learning accurate grammars which translate sentences into deductive database queries. The area of Learning Language in Logic (LLL) is producing a number of challenges to existing ILP theory and implementations. In particular, language applications of ILP require revision and extension of a hierarchically deened set of predicates in which the examples are typically only provided for predicates at the top of the hierarchy. New predicates often need to be invented, and complex recursion is usually involved. Advances in ILP theory and implementation related to the challenges of LLL are already producing beneecial advances in other sequence-oriented applications of ILP. In addition LLL is starting to develop its own character as a sub-discipline of AI involving the connuence of computational linguistics, machine learning and logic programming.