基于电信业务场景的智能问答机器人关键技术
Key Technology of IQA Robot Based on Telecom Scene
DOI: 10.12677/CSA.2017.74036, PDF, HTML, XML, 下载: 2,046  浏览: 2,985 
作者: 屠要峰*：中兴通讯，云计算研究院，江苏 南京
关键词: 智能问答；自然语言理解；机器学习；深度学习；Intelligent Question Answering； Natural Language Understanding； Machine Learning； Deep Earning
摘要: 智能问答系统[1]是一种针对自然语言理解的新型的信息交互方式。它的发展将带来新的人机交互模式，带来新的业务形态。智能问答系统涉及自然语言处理、知识管理、智能对话等多领域技术，本文以电信业务场景为例，提出了基于自然语言理解的智能问答系统架构，并对相关关键技术进行了深入分析。
Abstract: Intelligent question answering system is a new type of information interaction for natural lan-guage understanding. With the development of intelligent question answering system, it will bring new human-computer interaction mode and new business pattern. Intelligent question answering system involves many fields such as Natural Language Processing, knowledge management, intelligent dialogue and so on. In this paper, take the scene of telecom service for instance, we discuss that the architecture of Intelligent Question Answering System based on natural language understanding is put forward, and the related technologies are analyzed deeply.
文章引用：屠要峰. 基于电信业务场景的智能问答机器人关键技术[J]. 计算机科学与应用, 2017, 7(4): 291-300. https://doi.org/10.12677/CSA.2017.74036

参考文献

[1] 史忠植. 人工智能[M]. 北京: 机械工业出版社, 2001。
[2] http://money.163.com/16/1130/10/C745HHAB002580S6.html#from=keyscan
[3] http://finance.qq.com/a/20160302/004820.html
[4] 杜永萍, 黄萱菁, 吴立德. 模式学习在QA系统中的有效实现[J]. 计算机研究与发展, 2015, 43(3): 449-455.
[5] Russell, S.J., Norvig, P. 人工智能, 一种现代的方法[M]. 第3版. 北京: 清华大学出版社, 2013.
[6] http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns
[7] https://code.google.com/p/word2vec
[8] Graves, A. (2012) Supervised Sequence Labelling with Recurrent Neural Networks. Springer, Berlin.
[9] 李旺, 李绍滋. 基于DRT理论的汉语省略恢复研究[J]. 计算机工程, 2004, 30(17): 39-41.
[10] 宋洋, 王厚峰. 基于马尔可夫逻辑的中文零指代消解[J]. 计算机研究与发展,2015, 52(9): 2114-2122.
[11] Wu, Y., Schuster, M., Chen, Z., Le, Q.V., Norouzi, M., Macherey, W., et al. (2016) Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation.