Towards information-rich, logical text generation with knowledge-enhanced neural models
It addresses the issue of generic text generation in AI systems for applications like chatbots and content creation, but is incremental as it is a survey paper.
This survey reviews knowledge-enhanced text generation systems, which tackle the problem of neural models generating uninformative text by integrating external knowledge, summarizing progress in knowledge selection, understanding, and integration.
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.