Sciweavers

Share
ACL
2010

Bayesian Synchronous Tree-Substitution Grammar Induction and Its Application to Sentence Compression

10 years 11 months ago
Bayesian Synchronous Tree-Substitution Grammar Induction and Its Application to Sentence Compression
We describe our experiments with training algorithms for tree-to-tree synchronous tree-substitution grammar (STSG) for monolingual translation tasks such as sentence compression and paraphrasing. These translation tasks are characterized by the relative ability to commit to parallel parse trees and availability of word alignments, yet the unavailability of large-scale data, calling for a Bayesian tree-to-tree formalism. We formalize nonparametric Bayesian STSG with epsilon alignment in full generality, and provide a Gibbs sampling algorithm for posterior inference tailored to the task of extractive sentence compression. We achieve improvements against a number of baselines, including expectation maximization and variational Bayes training, illustrating the merits of nonparametric inference over the space of grammars as opposed to sparse parametric inference with a fixed grammar.
Elif Yamangil, Stuart M. Shieber
Added 10 Feb 2011
Updated 10 Feb 2011
Type Journal
Year 2010
Where ACL
Authors Elif Yamangil, Stuart M. Shieber
Comments (0)
books