Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review

TL;DR

This paper reviews how integrating knowledge and reasoning into natural language generation can enhance its ability to produce human-like, reasonable, and informative text, outlining goals, achievements, and future challenges.

Contribution

It proposes ten goals for knowledge-guided NLG systems and reviews recent progress in incorporating reasoning to improve human-like text generation.

Findings

Knowledge-guided NLG improves reasoning and informativeness

Recent techniques have achieved partial success in human-like text generation

Future challenges include integrating reasoning with diverse NLG applications

Abstract

The rapid development and application of natural language generation (NLG) techniques has revolutionized the field of automatic text production. However, these techniques are still limited in their ability to produce human-like text that is truly reasonable and informative. In this paper, we explore the importance of NLG being guided by knowledge, in order to convey human-like reasoning through language generation. We propose ten goals for intelligent NLG systems to pursue, and briefly review the achievement of NLG techniques guided by knowledge and reasoning. We also conclude by envisioning future directions and challenges in the pursuit of these goals.