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

DSpace/Manakin Repository

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

Citable link to this page

. . . . . .

Title: Bayesian Synchronous Tree-Substitution Grammar Induction and Its Application to Sentence Compression
Author: Yamangil, Elif; Shieber, Stuart M.

Note: Order does not necessarily reflect citation order of authors.

Citation: Yamangil, Elif and Stuart M. Shieber. 2010. Bayesian synchronous tree-substitution grammar induction and its application to sentence compression. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, Uppsala, Sweden, 11-16 July 2010. Association for Computational Linguistics. 937–947.
Full Text & Related Files:
Abstract: 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.
Published Version: http://www.aclweb.org/anthology/P/P10/P10-1096.pdf
Terms of Use: This article is made available under the terms and conditions applicable to Open Access Policy Articles, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#OAP
Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:4733833

Show full Dublin Core record

This item appears in the following Collection(s)

  • FAS Scholarly Articles [7219]
    Peer reviewed scholarly articles from the Faculty of Arts and Sciences of Harvard University
 
 

Search DASH


Advanced Search
 
 

Submitters