Deduction over Mixed-Level Logic Representations for Text Passage Retrieval

TL;DR

This paper presents a system that employs mixed-level logic representations and variable-depth search strategies to improve text passage retrieval by capturing different abstraction levels in natural language documents.

Contribution

It introduces a novel approach combining mixed-level Horn Clause Logic representations with variable-depth search for more effective passage retrieval.

Findings

Enhanced retrieval accuracy demonstrated in experiments

Applicable to various fields beyond NLP

Flexible search strategy adapts to document complexity

Abstract

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