Constituent Parsing with Incremental Sigmoid Belief Networks

Ivan Titov, James Henderson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We introduce a framework for syntactic parsing with latent variables based on a form of dynamic Sigmoid Belief Networks called Incremental Sigmoid Belief Networks. We demonstrate that a previous feed-forward neural network parsing model can be viewed as a coarse approximation to inference with this class of graphical model. By constructing a more accurate but still tractable
approximation, we significantly improve parsing accuracy, suggesting that ISBNs provide a good idealization for parsing. This generative model of parsing achieves state-of-theart results on WSJ text and 8% error reduction over the baseline neural network parser.
Original languageEnglish
Title of host publicationACL 2007, Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, June 23-30, 2007, Prague, Czech Republic
PublisherAssociation for Computational Linguistics
Pages632-639
Number of pages8
Publication statusPublished - 2007

Fingerprint Dive into the research topics of 'Constituent Parsing with Incremental Sigmoid Belief Networks'. Together they form a unique fingerprint.

Cite this