A Connectionist Architecture for Learning to Parse

13 years 7 months ago
A Connectionist Architecture for Learning to Parse
We present a connectionist architecture and demonstrate that it can learn syntactic parsing from a corpus of parsed text. The architecture can represent syntactic constituents, and can learn generalizations over syntactic constituents, thereby addressing the sparse data problems of previous connectionist architectures. We apply these Simple Synchrony Networks to mapping sequences of word tags to parse trees. After training on parsed samples of the Brown Corpus, the networks achieve precision and recall on constituents that approaches that of statistical methods for this task.
James Henderson, Peter Lane
Added 01 Nov 2010
Updated 01 Nov 2010
Type Conference
Year 1998
Where ACL
Authors James Henderson, Peter Lane
Comments (0)