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

ACL ID P10-1096
Title Bayesian Synchronous Tree-Substitution Grammar Induction and Its Application to Sentence Compression
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2010
Authors

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 align- ments, 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 sam- pling algorithm for posterior inference tai- lored 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 inf...