Mixed-Level Knowledge Representation and Variable-Depth Inference in Natural Language Processing

TL;DR

This paper introduces a system that employs mixed-level knowledge representation and variable-depth inference to improve natural language processing, with potential applications beyond NLP.

Contribution

It presents a novel approach combining mixed-level Horn Clause Logic with variable-depth search for enhanced document understanding.

Findings

Effective in representing natural language meaning

Improves passage retrieval accuracy

Applicable to fields beyond NLP

Abstract

A system is described that uses a mixed-level knowledge representation based on standard Horn Clause Logic to represent (part of) the meaning of natural language documents. A variable-depth search strategy is outlined that distinguishes between the different levels of abstraction in the knowledge representation to locate specific passages in the documents. A detailed description of the linguistic aspects of the system is given. Mixed-level representations as well as variable-depth search strategies are applicable in fields outside that of NLP.