, Volume 44, Issue 3, pp 211243
First online:
On Exact Learning of Unordered Tree Patterns
 Thomas R. AmothAffiliated withDepartment of Computer Science, Oregon State University
 , Paul CullAffiliated withDepartment of Computer Science, Oregon State University
 , Prasad TadepalliAffiliated withDepartment of Computer Science, Oregon State University
Abstract
Tree patterns are natural candidates for representing rules and hypotheses in many tasks such as information extraction and symbolic mathematics. A tree pattern is a tree with labeled nodes where some of the leaves may be labeled with variables, whereas a tree instance has no variables. A tree pattern matches an instance if there is a consistent substitution for the variables that allows a mapping of subtrees to matching subtrees of the instance. A finite union of tree patterns is called a forest. In this paper, we study the learnability of tree patterns from queries when the subtrees are unordered. The learnability is determined by the semantics of matching as defined by the types of mappings from the pattern subtrees to the instance subtrees. We first show that unordered tree patterns and forests are not exactly learnable from equivalence and subset queries when the mapping between subtrees is onetoone onto, regardless of the computational power of the learner. Tree and forest patterns are learnable from equivalence and membership queries for the onetoone into mapping. Finally, we connect the problem of learning tree patterns to inductive logic programming by describing a class of tree patterns called Clausal trees that includes nonrecursive singlepredicate Horn clauses and show that this class is learnable from equivalence and membership queries.
 Title
 On Exact Learning of Unordered Tree Patterns
 Journal

Machine Learning
Volume 44, Issue 3 , pp 211243
 Cover Date
 200109
 DOI
 10.1023/A:1010971904477
 Print ISSN
 08856125
 Online ISSN
 15730565
 Publisher
 Kluwer Academic Publishers
 Additional Links
 Topics
 Keywords

 ILP
 tree patterns
 exact learning
 learning from queries
 Industry Sectors
 Authors

 Thomas R. Amoth ^{(1)}
 Paul Cull ^{(1)}
 Prasad Tadepalli ^{(1)}
 Author Affiliations

 1. Department of Computer Science, Oregon State University, Corvallis, OR, 97331, USA