Knowledge-enhanced Neural Machine Reasoning: A Review

TL;DR

This review comprehensively examines recent advancements in knowledge-enhanced neural reasoning, categorizing methods, analyzing their strengths and limitations, and discussing future research prospects in diverse application domains.

Contribution

It introduces a novel taxonomy categorizing existing methods into two primary categories and four subcategories, providing a systematic analysis of their correlations and limitations.

Findings

Categorized existing methods into two main groups and four subgroups.

Identified strengths and limitations of current knowledge-enhanced reasoning techniques.

Discussed application domains and future research directions.

Abstract

Knowledge-enhanced neural machine reasoning has garnered significant attention as a cutting-edge yet challenging research area with numerous practical applications. Over the past few years, plenty of studies have leveraged various forms of external knowledge to augment the reasoning capabilities of deep models, tackling challenges such as effective knowledge integration, implicit knowledge mining, and problems of tractability and optimization. However, there is a dearth of a comprehensive technical review of the existing knowledge-enhanced reasoning techniques across the diverse range of application domains. This survey provides an in-depth examination of recent advancements in the field, introducing a novel taxonomy that categorizes existing knowledge-enhanced methods into two primary categories and four subcategories. We systematically discuss these methods and highlight their correlations, strengths, and limitations. Finally, we elucidate the current application domains and provide insight into promising prospects for future research.