Inducing Compact but Accurate Tree-Substitution Grammars

Trevor Cohn, Sharon Goldwater, Phil Blunsom

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

Abstract

Tree substitution grammars (TSGs) are a compelling alternative to context-free grammars for modelling syntax. However, many popular techniques for estimating weighted TSGs (under the moniker of Data Oriented Parsing) suffer from the problems of inconsistency and over-fitting. We present a theoretically principled model which solves these problems using a Bayesian non-parametric formulation. Our model learns compact and simple grammars, uncovering latent linguistic structures (e.g., verb subcategorisation), and in doing so far out-performs a standard PCFG.
Original languageEnglish
Title of host publicationProceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Place of PublicationBoulder, Colorado
PublisherAssociation for Computational Linguistics
Pages548-556
Number of pages9
ISBN (Print)978-1-932432-41-1
Publication statusPublished - 1 Jun 2009

Fingerprint

Dive into the research topics of 'Inducing Compact but Accurate Tree-Substitution Grammars'. Together they form a unique fingerprint.

Cite this