Abstract

We present a context-based system for unrestricted parsing of natural language and evaluate it on sentences from the Japanese newspaper Mainichi. Applying machine learning techniques, the system uses parse action examples generated from a treebank to generate a deterministic shift-reduce parser in the form of a decision structure. It relies heavily on context as encoded in features which describe the morphological, syntactic, semantic and other aspects of a given parse state.

Date

January 1, 1970

Authors

Ulf Hermjakob

Journal

katta

Volume

6

Pages

8