arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.00814cs.AI
收藏

使用知识增强的神经模型实现信息丰富的逻辑文本生成

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

Northwestern Polytechnical University(西北工业大学);Microsoft Research(微软研究院)

Hao Wang, Bin Guo, Wei Wu, Zhiwen Yu

摘要:

文本生成系统在深度学习技术的推动下取得了巨大的进步,并在生活中得到了广泛的应用。然而,现有的端到端神经模型存在倾向于生成无信息和通用文本的问题,因为它们不能将输入上下文与背景知识结合起来。为了解决这一问题,许多研究者开始考虑在文本生成系统中结合外部知识,即知识增强的文本生成。知识增强文本生成的挑战包括如何从大规模的知识库中选择合适的知识,如何阅读和理解提取的知识,以及如何将知识整合到生成过程中。本文综述了知识增强文本生成系统的研究进展,并提出了一些有待解决的问题和研究方向。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑