数据与计算发展前沿 ›› 2021, Vol. 3 ›› Issue (3): 111-125.

doi: 10.11871/jfdc.issn.2096-742X.2021.03.010

• 技术与应用 • 上一篇    下一篇

短文本自动生成技术研究进展

张晨阳1,2(),杜义华1,*()   

  1. 1.中国科学院计算机网络信息中心,北京100190
    2.中国科学院大学,北京100049
  • 收稿日期:2021-01-06 出版日期:2021-06-20 发布日期:2021-07-09
  • 通讯作者: 杜义华
  • 作者简介:张晨阳,中国科学院计算机网络信息中心,硕士研究生,主要研究方向为文本生成,网络传播引导技术。
    本文中承担的工作为:方法调研,模型及应用对比分析,论文撰写。
    ZhANG Chenyang is a postgraduate student in the Computer Network Information Center, Chinese Academy of Science. Her research interests include natural language generation and network communication broadcast and guidance technology.
    In this paper, she is responsible for method reviews, comparative analysis of models and applications, and paper writing.
    E-mail: zhangchenyang@cnic.cn|杜义华, 中国科学院计算机网络信息中心,副研究员,硕士生导师,主要研究方向为软件系统设计、网络传播引导技术。曾参加或负责中国科学院MIS系统、资源规划系统(ARP)、网络化信息发布平台(网站群)、科研管理数据集成及应用技术研究、信息化管理与决策支持工程等建设与运维项目。当前负责互联网信息传播引导技术的研究与示范、新媒体科学传播平台建设等项目。
    本文中承担的工作为:论文思路解析及论文统稿。
    DU Yihua is an associate Researcher and the master tutor of the Computer Network Information Center, Chinese Academy of Science. His research interests include software system design, and network communication broadcast and guidance technology. He has participated in the construction and opera-tion of the MIS system, resource planning system (ARP), network information publishing platform (website group), research mana-gement data integration and application technology research, information management and decision support engineering. He is currently responsible for the research and demonstration of Internet information dissemination guidance technology and the construction of new media science communication platform.
    In this paper, he is responsible for idea analysis and finalization.
    E-mail: yhdu@cashq.ac.cn
  • 基金资助:
    中国科学院战略性先导科技专项(C类)资助“互联网信息传播引导技术研究及示范”(XDC02060000)

A Survey on Short-text Generation Technology

ZHANG Chenyang1,2(),DU Yihua1,*()   

  1. 1. Computer Network Information Center, Chinese Academy of Science, Beijing 100190, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2021-01-06 Online:2021-06-20 Published:2021-07-09
  • Contact: DU Yihua

摘要:

【背景】 短文本自动生成技术的研究对阅读与写作效率的提升、传播与引导影响力提升、智能人机交互满意度和机器语义理解能力的提升等都有重要意义。但生成技术的发展和实际应用需求难度的提升使得短文本自动生成技术面临着诸多困难与挑战。【方法】 基于神经网络的生成方法作为人工智能领域的关键技术,在短文本摘要、对话生成、评论文本生成、诗歌创作等任务中都取得了很多创新性成果。【结果】 本文对基于神经网络的短文本自动生成技术在生成模型、应用需求、评估指标等方面的研究进展进行了介绍和梳理,为短文本自动生成技术的进一步研究提供了参考。【结论】 本文总结了基于神经网络的短文本自动生成技术的发展现状并进一步提出了未来的发展趋势。

关键词: 自然语言生成, 神经网络模型, 短文本, 评价方法

Abstract:

[Context] Research on short-text generation is of great importance in improving the efficiency of reading and writing, the impact of communication and guidance, the satisfaction of intelligent human-computer interaction and the capacity for machine semantic comprehension. However, short-text generation technology faces many difficulties and challenges due to the weakness of generation technology and the increasing complexity of realistic implementation requirements.[Methods] The neural network based generation method is a key artificial intelligence technology that has accomplished several pioneering achievements in short-text summary, dialogue generation, text generation of comments, poetry creation, and other linguistic tasks. [Results] This paper presents the research status and development of neural network based short-text generation technology in the aspects of the generation model, goal, and evaluation metric, providing a guide for further research into short-text generation technology. [Conclusions] we summarized the difficulties, challenges and trends of neural network based short-text generation technology.

Key words: Natural Language Generation (NLG), neural network model, short-text, evaluation method