该文讨论怎样利用语言知识资源来帮助机器进行语义理解和常识推理。首先,指出人类生活在常识和意义世界中,人工智能机器人必须理解自然语言的意义,能够在此基础上进行常识推理。接着,简单梳理了基于知识和基于统计两种自然语言处理路线各自的优长和短缺。然后,说明完全绕开知识的统计方法和深度学习,都不能真正理解概念和语言。该文通过具体案例说明,《实词信息词典》已经配备了有关词项的语义角色关系及其句法配置信息;把这种语言知识加入知识图谱和内容计算中,可以为人工智能提供理解和解释从而造就一种可解释的人工智能。由于“物性角色”描述了名词所指事物的百科知识,可用以回答相关事物是什么(形式角色)、有哪些部件(构成角色)、用什么做的(材料)、怎么形成的(施成)、有什么用途(功用)等常识性问题。
Abstract
This paper discusses how to use semantic resources to assist computer in semantic understanding and commonsense reasoning. Firstly, we point out that human beings live in a world with common sense and meaning, and that artificial intelligence robots are required to understand the meaning of natural language to make commonsense reasoning. Then, we briefly summarize the advantages and disadvantages of two approaches of natural language processing based on knowledge and statistics. Then, we explain that neither concepts nor language can be truly understood with statistical methods and Deep Learning can hardly account for any knowledge. The paper shows with specific cases that Information Dictionary of Notional Word has been equipped with semantic role information and syntactic configuration of the words, which can be employed in the knowledge graph and the content computing and served for the improvement of the artificial intelligence. As the "Qualia Role" describes the encyclopedic knowledge of nouns, it can be used to answer commonsense questions such as what it is (formal role), what it consists of (constitute role), what it is made of (material role), how it is created (agentive role), and what it is used for (telic role).
关键词
语言知识资源 /
语义理解 /
常识推理 /
基于知识/统计 /
语义角色 /
物性角色
{{custom_keyword}} /
Key words
semantic knowledge resources /
semantic understanding /
commonsense reasoning /
knowledge based / statistics based /
semantic role /
qualia role
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Chomsky Noam.The science of language: Interviews with James McGilvray[M].Cambridge University Press,2011.(曹道根,胡朋志,译.语言的科学: 詹姆斯·麦克吉尔弗雷访谈录.北京: 商务印书馆,2015: 226-238.)
[2] Pinker Steven.The stuff of thought: Language as a window into human nature[M].New York: Penguin Groups,Viking Press,2007.(张旭红,梅德明,译.思想本质: 语言洞察人类天性之窗.杭州: 浙江人民出版社,2015: 332.)
[3] Daniel Bor.The ravenous brain: How the new science of consciousness explains our insatiable search for meaning[M].Basic Books,2012.(林旭文,译.贪婪的大脑: 为何人类会无止境地寻求意义.北京: 机械工业出版社,2013: 2-3.)
[4] 白硕.人工智能的诗与远方: 一文读懂NLP起源、流派和技术[EB/OL].http://mp.weixin.qq.com/s/VpWabo7_ekA7j_fw2ZuDdA.2018-1-11.
[5] Winograd Terry.Language as a cognitive process[M].Addison-Wesley Publishing Company Inc.,1983.
[6] Mugan Jonathan.The two paths from natural language processing to artificial intelligence[EB/OL].https://medium.com/intuitionmachine/the-two-paths-from-natural-language-processing-to-artificial-intelligence-d5384ddbfc18.2017-2-9.
[7] Hassler Susan.马文·明斯基与人工智能之探[J].科技纵览(IEEE Spectrum),2016(3):8.
[8] 罗兰德·豪塞尔.A computational model of natural language communication——Interpretation,inference and production in database semantics[M].Springer Science & Business Media,2006.(冯秋香,译;冯志伟审校.自然语言交流的计算机模型——数据库语义学下的语言理解、推理和生成.北京: 商务印书馆,2016: 前言,第xi页.)
[9] Marcus Gary.Deep learning: A critical appraisal[J].arXiv preprint arXiv:1801.00631,2018.
[10] 文强,刘小芹.AAAI前主席回怼马库斯[EB/OL].https://mp.weixin.qq.com/s/Z0KEPCz3U51EtxBbzfh_jQ.2018-1-5
[11] Yann LeCun.深度学习已死,可微分编程万岁[EB/OL].https://mp.weixin.qq.com/s/xyjrr5uWGP-oYsRWCqqTDg.2018-1-6.
[12] 金丝猴.为什么知识图谱终于火了？[EB/OL].http://baijiahao.baidu.com/s?id=1585311312955034812&wfr=spider&for=pc.2017-11-28.
[13] 朱松纯.浅谈人工智能: 现状、任务、构架与统一[EB/OL].https://mp.weixin.qq.com/s/-wSYLu-XvOrsST8_KEUa-Q.2017-11-2.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
教育部人文社会科学重点研究基地重大研究项目(18JJD740003);国家语委重点项目(ZDI135-76);教育部人文社会科学研究青年项目(16YJC740050)
{{custom_fund}}
PDF(1806 KB)
