Automatic Extraction of Subcategorization from Corpora

Abstract

We describe a novel technique and implemented system for constructing a subcategorization dictionary from textual corpora. Each dictionary entry encodes the relative frequency of occurrence of a comprehensive set of subcategorization classes for English. An initial experiment, on a sample of 14 verbs which exhibit multiple complementation patterns, demonstrates that the technique achieves accuracy comparable to previous approaches, which are all limited to a highly restricted set of subcategorization classes. We also demonstrate that a subcategorization dictionary built with the system improves the accuracy of a parser by an appreciable amount.

8 pages; requires aclap.sty. To appear in ANLP-97

References in corpus (4)

• Developing and Evaluating a Probabilistic LR Parser of Part-of-Speech and Punctuation Labels
• Comlex Syntax: Building a Computational Lexicon
• Apportioning Development Effort in a Probabilistic LR Parsing System through Evaluation
• Does Baum-Welch Re-estimation Help Taggers?

Cited by in corpus (3)

• Automatic Extraction of Subcategorization Frames for Czech
• Considering a resource-light approach to learning verb valencies
• Optimality Theory as a Framework for Lexical Acquisition