Towards information-rich, logical text generation with knowledge-enhanced neural models

TL;DR

This paper reviews knowledge-enhanced neural text generation, addressing challenges in knowledge selection, understanding, and integration to produce more informative and logical texts.

Contribution

It provides a comprehensive survey of current methods, summarizes progress, and discusses open issues and future research directions in knowledge-enhanced text generation.

Findings

Summarizes recent advances in knowledge selection and integration.

Identifies key challenges and open issues in the field.

Proposes future research directions for more effective knowledge use.

Abstract

Text generation system has made massive promising progress contributed by deep learning techniques and has been widely applied in our life. However, existing end-to-end neural models suffer from the problem of tending to generate uninformative and generic text because they cannot ground input context with background knowledge. In order to solve this problem, many researchers begin to consider combining external knowledge in text generation systems, namely knowledge-enhanced text generation. The challenges of knowledge enhanced text generation including how to select the appropriate knowledge from large-scale knowledge bases, how to read and understand extracted knowledge, and how to integrate knowledge into generation process. This survey gives a comprehensive review of knowledge-enhanced text generation systems, summarizes research progress to solving these challenges and proposes some open issues and research directions.