知识增强的自然语言生成研究综述  

Survey of Knowledge-enhanced Natural Language Generation Research

作　　者：梁明轩 王石[2] 朱俊武[1] 李阳 高翔[1,2] 焦志翔 LIANG Mingxuan;WANG Shi;ZHU Junwu;LI Yang;GAO Xiang;JIAO Zhixiang(College of Information Engineering,Yangzhou University,Yangzhou,Jiangsu 225000,China;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China)

机构地区：[1]扬州大学信息工程学院,江苏扬州225000 [2]中国科学院计算技术研究所,北京100190

出　　处：《计算机科学》2023年第S01期1-8,共8页Computer Science

基　　金：国家242信息安全计划项目(2021A008);北京市科技新星计划交叉学科合作课题(Z191100001119014);国家重点研发计划重点专项(2017YFC1700300,2017YFB1002300);国家自然科学基金(61702234)。

摘　　要：自然语言生成(Natural Language Generation,NLG)任务是自然语言处理(Natural Languge Processing,NLP)任务中的一个子类,并且是一项具有挑战性的任务。随着深度学习在自然语言处理中的大量应用,其已经变成自然语言生成中处理各种任务的主要方法。自然语言生成任务中主要有问答任务、生成摘要任务、生成评论任务、机器翻译任务、生成式对话任务等。传统的生成模型依赖输入文本,基于有限的知识生成文本。为解决这个问题,引入了知识增强的方法。首先介绍了自然语言生成的研究背景和重要模型,然后针对自然语言处理归纳介绍了提高模型性能的方法,以及基于内部知识(如提取关键词增强生成、围绕主题词等)和外部知识(如借助外部知识图谱增强生成)集成到文本生成过程中的方法和架构。最后,通过分析生成任务面临的一些问题,讨论了未来的挑战和研究方向。Natural language generation(NLG)task is a subclass of natural language processing(NLP)tasks and is a challenging task.With the massive application of deep learning in natural language processing,it has become the main method for handling various tasks in natural language generation.The main natural language generation tasks are question and answer tasks,summary generation tasks,comment generation tasks,machine translation tasks,generative dialogue tasks,etc.Traditional generative mo-dels rely on input text to generate text based on limited knowledge,and knowledge enhancement methods are introduced to solve this problem.Firstly,the research background and important models of natural language generation are introduced.Then,methods to improve model performance are introduced for natural language processing induction,and the methods and architectures based on the integration of internal knowledge(such as extracting keywords to enhance generation,surrounding subject words,etc.)and external knowledge(such as enhanced generation with the help of external knowledge graph)into the text generation process are introduced..Finally,the future challenges and research directions are discussed by analyzing some problems faced by the generation task.

关 键 词：自然语言生成 知识增强 深度学习 知识图谱 关键词提取 主题词 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]