Natural Language QA Approaches using Reasoning with External Knowledge

TL;DR

This paper surveys recent approaches to natural language question answering that incorporate reasoning with external knowledge, highlighting the integration of traditional AI reasoning with modern NLP techniques.

Contribution

It provides a comprehensive overview of recent work on NLQA using external knowledge, bridging knowledge representation and NLP fields.

Findings

External knowledge enhances NLQA performance.

Recent datasets and models focus on reasoning with external knowledge.

Integration of reasoning and NLP is a growing research trend.

Abstract

Question answering (QA) in natural language (NL) has been an important aspect of AI from its early days. Winograd's ``councilmen'' example in his 1972 paper and McCarthy's Mr. Hug example of 1976 highlights the role of external knowledge in NL understanding. While Machine Learning has been the go-to approach in NL processing as well as NL question answering (NLQA) for the last 30 years, recently there has been an increasingly emphasized thread on NLQA where external knowledge plays an important role. The challenges inspired by Winograd's councilmen example, and recent developments such as the Rebooting AI book, various NLQA datasets, research on knowledge acquisition in the NLQA context, and their use in various NLQA models have brought the issue of NLQA using ``reasoning'' with external knowledge to the forefront. In this paper, we present a survey of the recent work on them. We believe our survey will help establish a bridge between multiple fields of AI, especially between (a) the traditional fields of knowledge representation and reasoning and (b) the field of NL understanding and NLQA.