This is a basic Java implementation of Andreas Stolcke's probabilistic Earley parser:

Andreas Stolcke. 1995. An Efficient Probabilistic Context-Free Parsing Algorithm that Computes Prefix Probabilities. Computational Linguistics 21(2), 165-201.

There is also useful library code to interface with treebanks and train probabilistic context-free grammars for use with the parser. You will need a JVM version 1.4 or later to run it.

Download it here.

Contact Roger Levy, rlevy[at]inf.ed.ac.uk, for questions regarding the parser.