Abstract

We present a novel generative model for natural language tree structures in which semantic (lexical dependency) and syntactic (PCFG) structures are scored with separate models. This factorization provides conceptual simplicity, straightforward opportunities for separately improving the component models, and a level of performance comparable to similar, non-factored models. Most importantly, unlike other modern parsing models, the factored model admits an extremely effective A* parsing algorithm, which enables efficient, exact inference.

Keywords

Computer scienceParsingArtificial intelligenceInferenceNatural language processingDependency (UML)Bottom-up parsingDependency grammarGenerative grammarSimplicityTop-down parsingNatural languageParser combinatorComponent (thermodynamics)Top-down parsing languageGenerative modelTree (set theory)Programming languageMathematics

Affiliated Institutions

Related Publications

ASPECTS OF THE THEORY OF SYNTAX

Abstract : Contents: Methodological preliminaries: Generative grammars as theories of linguistic competence; theory of performance; organization of a generative grammar; justifi...

1964 10932 citations

Publication Info

Year
2002
Type
article
Volume
15
Pages
3-10
Citations
745
Access
Closed

External Links

Citation Metrics

745
OpenAlex

Cite This

Dan Klein, Christopher D. Manning (2002). Fast Exact Inference with a Factored Model for Natural Language Parsing. , 15 , 3-10.