A Computational Effective Document Semantic Representation

Abstract

A technique based on noun phrase and verb clause slot structures Is described for representing the semantics of the sentences making up a text document. Thesaurus head word index numbers are placed in the appropriate document sentence clause slots to represent the meta level meaning of the sentences. Many different expressions of the same document content can thus be represented by one semantic representation. An implementation of such a technique is described, and sample output is presented. The document summarisation thus produced is suitable for manipulation by computers for a variety of document processing tasks. The technique has primarily been developed for an automated essay grading system, where a robust context free representation of documents is required.