Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (5): 1227-1235.DOI: 10.11772/j.issn.1001-9081.2020071069

Special Issue: 人工智能 综述

• Artificial intelligence •     Next Articles

Summarization of natural language generation

LI Xueqing1,2, WANG Shi2, WANG Zhujun1,2, ZHU Junwu1   

  1. 1. College of Information Engineering, Yangzhou University, Yangzhou Jiangsu 225000, China;
    2. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
  • Received:2020-07-23 Revised:2020-10-21 Online:2020-12-23 Published:2021-05-10
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61872313), the Key Project of National Key Research and Development Program of China (2017YFB1002300, 2018YFC1700302).

自然语言生成综述

李雪晴1,2, 王石2, 王朱君1,2, 朱俊武1   

  1. 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
  • 通讯作者: 王石
  • 作者简介:李雪晴(1995-),女,江苏泰州人,博士研究生,主要研究方向:自然语言处理;王石(1981-),男,山东博兴人,副研究员,博士,主要研究方向:语义分析、知识图谱;王朱君(1996-),男,江苏东台人,硕士研究生,主要研究方向:自然语言处理;朱俊武(1972-),男,江苏江都人,教授,博士,CCF高级会员,主要研究方向:知识工程、本体论。
  • 基金资助:
    国家自然科学基金资助项目(61872313);国家重点研发计划重点专项(2017YFB1002300,2018YFC1700302)。

Abstract: Natural Language Generation (NLG) technologies use artificial intelligence and linguistic methods to automatically generate understandable natural language texts. The difficulty of communication between human and computer is reduced by NLG, which is widely used in machine news writing, chatbot and other fields, and has become one of the research hotspots of artificial intelligence. Firstly, the current mainstream methods and models of NLG were listed, and the advantages and disadvantages of these methods and models were compared in detail. Then, aiming at three NLG technologies:text-to-text, data-to-text and image-to-text, the application fields, existing problems and current research progresses were summarized and analyzed respectively. Furthermore, the common evaluation methods and their application scopes of the above generation technologies were described. Finally, the development trends and research difficulties of NLG technologies were given.

Key words: Natural Language Generation (NLG), linguistics, natural language processing, evaluation method, text-to-text generation, data-to-text generation, image-to-text generation

摘要: 自然语言生成(NLG)技术利用人工智能和语言学的方法来自动地生成可理解的自然语言文本。NLG降低了人类和计算机之间沟通的难度,被广泛应用于机器新闻写作、聊天机器人等领域,已经成为人工智能的研究热点之一。首先,列举了当前主流的NLG的方法和模型,并详细对比了这些方法和模型的优缺点;然后,分别针对文本到文本、数据到文本和图像到文本等三种NLG技术,总结并分析了应用领域、存在的问题和当前的研究进展;进而,阐述了上述生成技术的常用评价方法及其适用范围;最后,给出了当前NLG技术的发展趋势和研究难点。

关键词: 自然语言生成, 语言学, 自然语言处理, 评价方法, 文本到文本生成, 数据到文本生成, 图像到文本生成

CLC Number: