Can Subcategorisation Probabilities Help a Statistical Parser?

Abstract

Research into the automatic acquisition of lexical information from corpora is starting to produce large-scale computational lexicons containing data on the relative frequencies of subcategorisation alternatives for individual verbal predicates. However, the empirical question of whether this type of frequency information can in practice improve the accuracy of a statistical parser has not yet been answered. In this paper we describe an experiment with a wide-coverage statistical grammar and parser for English and subcategorisation frequencies acquired from ten million words of text which shows that this information can significantly improve parse accuracy.

9 pages, uses colacl.sty

References in corpus (2)

• Valence Induction with a Head-Lexicalized PCFG
• Apportioning Development Effort in a Probabilistic LR Parsing System through Evaluation

Cited by in corpus (6)

• Corpus Annotation for Parser Evaluation
• Learning Transformation Rules to Find Grammatical Relations
• Automatic Extraction of Subcategorization Frames for Czech
• Integrating Multiple Knowledge Sources for Robust Semantic Parsing
• Predicting the Argumenthood of English Prepositional Phrases
• Optimality Theory as a Framework for Lexical Acquisition