Paper: Automatic Extraction Of Subcategorization From Corpora

ACL ID A97-1052
Title Automatic Extraction Of Subcategorization From Corpora
Venue Applied Natural Language Processing Conference
Session Main Conference
Year 1997

We describe a novel technique and imple- mented system for constructing a subcate- gorization dictionary from textual corpora. Each dictionary entry encodes the relative frequency of occurrence of a comprehen- sive set of subcategorization classes for En- glish. An initial experiment, on a sample of 14 verbs which exhibit multiple comple- mentation patterns, demonstrates that the technique achieves accuracy comparable to previous approaches, which are all limited to a highly restricted set of subcategoriza- tion classes. We also demonstrate that a subcategorization dictionary built with the system improves the accuracy of a parser by an appreciable amount 1. 1 Motivation Predicate subcategorization is a key component of a lexical entry, because most, if not all, recent syn- tactic theories...