http:^^www.cs.wisc.edu^~pubs^faculty-info^sklein.html
来自「This data set contains WWW-pages collect」· HTML 代码 · 共 98 行
HTML
98 行
Date: Thu, 07 Nov 1996 19:07:19 GMTServer: NCSA/1.5Content-type: text/htmlLast-modified: Fri, 05 Jan 1996 19:49:51 GMTContent-length: 3473<HTML><HEAD><TITLE> Home Page of Sheldon Klein </TITLE></HEAD><BODY><H1> <!WA0><IMG ALIGN=MIDDLE SRC="http://www.cs.wisc.edu/~pubs/faculty-info/klein.gif"> Sheldon Klein </H1><BLOCKQUOTE> Professor of Computer Sciences and Linguistics <BR> <BR> Computer Sciences Department <BR> University of Wisconsin <BR> 1210 W. Dayton St. <BR> Madison, WI 53706-1685 <BR> <BR> telephone: (608) 262-1204 <BR> fax: (608) 262-9777 <BR> email: <!WA1><A HREF="mailto:sklein@cs.wisc.edu"> sklein@cs.wisc.edu</A> <BR></BLOCKQUOTE><EM>Ph.D., University of California, Berkeley, 1963</EM> <BR><EM>Interests:</EM>Meta-linguistic pragmatics of artificial intelligence and grammars,archaeology of knowledge structures, testing theories of languagechange and transmission <P><HR><H2> Research Summary </H2>My interests are expressed in two related research efforts: <P>1. The first involves a meta-linguistic, natural language processingsystem that can be configured to model a variety of theoreticallinguistic models. It's semantic structures are in the form ofa relational calculus that can be expressed in implicit semanticnetworks. The basic semantic units are objects and relations.Objects may be atoms of classes, or contain relational structures.Relations may be logical operators. All units in the system areassociated with Boolean feature vectors. During the course ofgeneration or recognition, inheritance of features is bi-directional.Because relations can be defined as logical operators, script-like,world knowledge rules can be encoded in the same notation usedto map semantic structures to syntactic units. Semantic/syntacticproduction rules are represented as data, and the same rules canbe used for both generation and recognition. The system can containmore than one grammar, thereby allowing it to be configured eitheras a machine translation system, or as a natural language interfaceto application command languages. <P>2. The combinatoric problems associated with unrestricted modelsof human language processing suggest that real-world knowledgesystems may have evolved in forms that make combinatoric processingproblems linear. I am currently investigating the role of Booleangroups and analogy in complex behavioral systems, including therepresentation of categorial grammars. Grammars in this notationcan readily be implemented in connectionist models, and may providea transparent means of linking language structure to neural nettheory. My research effort has occasionally involved analysisof archaeological materials as early as the Middle-to-Upper Paleolithictransition. <P><H2> Sample Recent Publications </H2>Human cognitive changes at the middle to upper Paleolithic transition:The evidence of Boker Tachtit, in <EM>The Emergence of ModernHumans: An Archaeological Perspective</EM>, P. Mellars, ed., pp.499-516, Edinburgh University Press, Edinburgh, 1990. <P> The invention of computationally plausible knowledge systems inthe upper Paleolithic, in <EM>The Origins of Human Behaviour</EM>,R. Foley, ed., pp. 67-81, Unwin Hyman, London, 1991. <P> Grammars, the I Ching and Levi-Strauss: More on Siemens' `ThreeFormal Theories of Cultural Analogy', to appear in <EM>Journalof Quantitative Anthropology</EM>. <P> <HR><ADDRESS> This page was automatically created October 4, 1995.<BR> Email <!WA2><A HREF="mailto:pubs@cs.wisc.edu">pubs@cs.wisc.edu</A>to report errors.</ADDRESS><HR></BODY></HTML>⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?