semantic network最全的资料集

Semantic Networks

(Click on "Semantic" to do a Google search on "semantic network";
click on "Networks" to do a Google search on "semantic networks".)

Last Update: 10 November 2008

Note: NEW or UPDATED material is highlighted


A username and password may be required for some online papers. Please contact Bill Rapaport.


  1. History:

  • Arguably the first modern paper on semantic networks.

  1. The Tree of Porphyry

  2. Masterman, M.M. (1957), "The Thesaurus in Syntax and Semantics", Mechanical Translation 4(1/2) (November): 35-43.

  3. Kruja, Eriola; Marks, Joe; Blair, Ann; & Waters, Richard (2001), "A Short Note on the History of Graph Drawing", Proceedings of the 9th International Symposium on Graph Drawing (GD 2001, Vienna) (Berlin: Springer Lecture Notes in Computer Science 2265): 272-286.

3 Semantic-Network-based theories:

  • An important paper on the first semantic-network knowledge-representation-and-reasoning system in AI, and how to get it to read and comprehend a natural-language text.

  • If you are off-campus, you may need to enter your UBIT username and password.

  • Other journals (e.g., Language, Proc. IRE) can be accessed in a similar fashion;
    most have much simpler interfaces than the one described here for Psych. Bul., Psych. Rev., and Amer. Psych.!

  • To access articles from Psychological Bulletin, Psychological Review, or American Psychologist:

  • SNePS (Semantic Network Processing System) is a KRRA system created by Stuart C. Shapiro and developed by him in collaboration with numerous colleagues and students.

  1. Link to: UB Libraries Electronic Journals.

  2. Type the journal title into the Search box and click the "Search" button.

  3. Click on "Journals@Ovid PsycArticles".

  4. Find the volume and number that you are looking for (click the red "Next" button to go to earlier issues).

  5. Click the "Table of Contents" button for the issue you want.

  6. Find the article in the table of contents, and then click either
    "Complete Reference" for a full citation with abstract, or
    "Ovid Full Text" to download a PDF copy of the article.

  7. The SNePS Knowledge Representation, Reasoning, and Acting System

  8. Quillian's semantic-network theory (one of the earliest in AI):

  9. Roger Schank's theory of Conceptual Dependency.

Some references:

  • LOCKWOOD Book Collection Q335 .P7 1991

  • SCI/ENGR Book Collection Q360 .A87

  • Contains the first major paper on SNePS (there were earlier ones in conference publications; see the full SNeRG bibliography):

Shapiro, Stuart C.

(1979), "The SNePS Semantic Network Processing System", pp. 179-203.

  1. Findler, Nicholas V. (ed.) (1979), Associative Networks: The Representation and Use of Knowledge by Computers (New York: Academic Press).

  2. Evens, Martha Walton (ed.) (1988), Relational Models of the Lexicon: Representing Knowledge in Semantic Networks (Cambridge, UK: Cambridge University Press).

  3. Sowa, John F. (ed.) (1991), Principles of Semantic Networks: Explorations in the Representation of Knowledge (San Mateo, CA: Morgan Kaufmann).

  4. Lehmann, Fritz (ed.) (1992), Semantic Networks in Artificial Intelligence (Oxford: Pergamon Press).

On the relationship between first-order logic and semantic networks:

  • 2 papers (and a review) on the difficulty of representing meta-knowledge in FOL:

  • 3 papers on how SNePS handles the problem:

Abstract: Cognitive agents, whether human or computer, that engage in natural-language discourse and that have beliefs about the beliefs of other cognitive agents must be able to represent objects the way they believe them to be and the way they believe others believe them to be. They must be able to represent other cognitive agents both as objects of beliefs and as agents of beliefs. They must be able to represent their own beliefs, and they must be able to represent beliefs as objects of beliefs. These requirements raise questions about the number of tokens of the belief representation language needed to represent believers and propositions in their normal roles and in their roles as objects of beliefs. In this paper, we explicate the relations among nodes, mental tokens, concepts, actual objects, concepts in the belief spaces of an agent and the agent's model of other agents, concepts of other cognitive agents, and propositions. We extend, deepen, and clarify our theory of intensional knowledge representation for natural-language processing, as presented in previous papers and in light of objections raised by others. The essential claim is that tokens in a knowledge-representation system represent only intensions and not extensions. We are pursuing this investigation by building CASSIE, a computer model of a cognitive agent and, to the extent she works, a cognitive agent herself. CASSIE's mind is implemented in the SNePS knowledge-representation and reasoning system.
  1. Israel, David J. & Brachman, Ronald J. (1981), "Distinctions and Confusions: A Catalogue Raisonné", Proceedings of the 7th International Joint Conference on Artificial Intelligence (IJCAI-81, University of British Columbia) (Los Altos: William Kaufmann): 452-459.

  2. Schubert, Lenhart K. (1991), "Semantic Nets Are in the Eye of the Beholder", in John F. Sowa (ed.), Principles of Semantic Networks: Explorations in the Representation of Knowledge (San Mateo, CA: Morgan Kaufmann): 95-107.

  3. Shastri, Lokendra (1991), "Why Semantic Networks?", in John F. Sowa (ed.), Principles of Semantic Networks: Explorations in the Representation of Knowledge (San Mateo, CA: Morgan Kaufmann): 109-136.

  4. On the difficulty of representing meta-knowledge (knowledge about knowledge) in FOL and how it can be done in SNePS:

Other semantic-network-related KRR theories:

  1. Frames

  2. Description Logics

  3. Concept Maps

Semantic Networks and the Web:

  1. Original Posters of the Internet

  2. Members of the Clever Project (1999), "Hypersearching the Web", Scientific American (June): 54-60.

  3. Berners-Lee, Tim; Hendler, James; & Lassila, Ora (2001), "The Semantic Web", Scientific American (May): 35-43.

  4. Feigenbaum, Lee; Herman, Ivan; Hongsermeier, Tonya; Neumann, Eric; & Stephens, Susie (2007), "The Semantic Web in Action", Scientific American 297(6) (December): 90-97.

Miscellaneous:

  • Reprinted as Research Paper No. 74-RP-1013 (Defence and Civil Institute of Enviornmental Medicine, Defence Research Board)

  1. Taylor, M.M. (1974), "Speculations on Bilingualism and the Cognitive Network", Working Papers on Bilingualism, Issue 2 (Toronto: Ontario Institute for Studies in Education, Bilingual Education Project).

  2. Werner, Oswald (1988), "How to Teach a Network: Minimal Design Features for a Cultural Knowledge Acquisition Device or C-KAD", in Martha Walton Evens (ed.), Relational Models of the Lexicon: Representing Knowledge in Semantic Networks (Cambridge, UK: Cambridge University Press): 141-166.

  3. Hartley, Roger T.; & Barnden, John A. (1997), "Semantic Networks: Visualizations of Knowledge", Trends in Cognitive Sciences 1(5) (August): 169-175.

  4. NEW
    Special Issue on AI and Networks, AI Magazine 29(3) (Fall 2008).




Copyright © 2005-2008 by William J. Rapaport ( rapaport@cse.buffalo.edu)
http://www.cse.buffalo.edu/~rapaport/semantic-networks.html-20081110

 

 

 

 

 

 

http://www.cse.buffalo.edu/~rapaport/semantic-networks.html

转载于:https://my.oschina.net/airship/blog/375891

  • 0
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Semantic3D数据集是一个广泛用于训练和评估语义分割算法的公开数据集。它是为了解决在三维点云中进行语义分割任务而创建的。 该数据集使用了Velodyne 3D LiDAR扫描仪采集的真实世界场景点云数据。这些点云数据包含了丰富的语义信息,可以用于训练和测试语义分割算法。数据集中的点云按照城市和场景进行组织,包括不同类型的建筑物、路面、植被和其他物体。 为了使用Semantic3D数据集进行训练,首先需要将点云数据预处理成模型可以处理的格式。预处理过程中包括点云重采样、点云特征提取和类别标注等步骤。处理后的点云数据可以作为输入,配合对应的标签数据进行训练。 训练可以使用各种深度学习算法,如卷积神经网络(CNN)或全卷积网络(FCN)。这些神经网络可以学习从点云数据到语义类别的映射关系,从而实现语义分割任务。 在训练过程中,可以使用一些技术来提高模型性能,如数据增强、正则化和迁移学习。数据增强可以通过对点云进行旋转、平移和缩放等变换来扩充训练样本。正则化方法可以防止模型过拟合训练数据。迁移学习可以利用在其他任务上训练好的模型权重来加速训练过程。 通过使用Semantic3D数据集进行训练,可以让语义分割算法在三维点云数据上得到充分的训练和测试,从而提高算法在真实场景中的性能。这对于各种应用,如自动驾驶、机器人导航和环境监测等具有重要意义。

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值