Semantic Web: Solving Semantic Web's Chicken and Egg Problem with NLP

REGISTRATIONPriceQuantity
$15.00
$0.00

Description

  •  


    Title:  Solving Semantic Web's Chicken and Egg Problem with NLP

    In the first presentation, Dr. Barney Pell, CEO of Powerset, will describe his vision of Natural Language and the Semantic Web. The Semantic Web promises to revolutionize access to information by adding machine-readable semantic information to content which is normally interpretable only by people. In addition, it will also revolutionize access to services by adding semantic information to create machine-readable service descriptions.

    This ambitious vision has been slow to take off because of a chicken and egg problem. Markup is required before people will build applications, and applications are required before it is worth the hard work of doing markup. Natural language processing (NLP) has advanced to the point where it can break the impasse and open up the possibilities of the Semantic Web.  First, NLP systems can now automatically create annotations from unstructured text.  This provides the data that semantic web applications require. Second, NLP systems are themselves consumers of semantic web information and thus provide economic motivation for people to create and maintain such information.  For example, a new generation of natural language search systems, as illustrated by Powerset, can take advantage of semantic web markup and ontologies to augment their interpretation of underlying textual content. They can also expose semantic web services directly in response to natural language queries.

    The second presentation will be demonstration of Powset's NLP search engine and technology, given by Dr. Ron Kaplan, Chief Scientist at Powerset.

    Lots of cutting-edge researches in this field are happening in academics. We'll have Rion Snow, a PhD student at Stanford University, to present the Stanford Wordnet Project - Automatic Acquisition of Knowledge from Text. This talk describes their recent work in learning semantic relations and WordNet-like taxonomies from English text. The Stanford team uses machine learning methods to learn the hypernym (is a kind of) and coordinate term (is similar to) relations, and propose a model for inferring taxonomies that combine heterogenous evidence sources for maximal benefit. The Stanford Wordnet Project currently offers an augmented version of WordNet with 400,000 additional automatically-inferred hyponyms.

     

    Agenda:

    6:30pm - 7:00pm    Registration / Networking / Refreshments / Pizza

    7:00pm - 7:10pm    Community announcement

    7:10pm - 7:40pm    Barney Pell: Natural Language and Semantic Web

    7:40pm - 8:00pm    Ron Kaplan: Powerset demo and technolgy

    8:00pm - 8:20pm    Rion Snow: Stanford Wordnet Project

    8:20pm - 9:00pm    Q&A

    Contact: SIG co-chair AJ Chen (ajchen-at-web2express.org) or Jeff Pollock (jeff.pollock-at-oracle.com)

    Speaker Bios

    Barney Pell, Ph.D., Founder and CTO, Powerset
    For over fifteen years, Dr. Barney Pell, (Ph.D. Computer science, Cambridge University) has pursued ground breaking technical and commercial innovation in A.I. as a researcher, research manager, business strategist and entrepreneur. Prior to founding Powerset, he spent 2005 as Entrepreneur in Residence at Mayfield evaluating early to mid-stage IT and knowledge based companies. Before joining Mayfield, Dr. Pell worked for NASA Ames Research Center on two occasions: from 1993-1998 as Project Lead for the Executive component of the prize-winning Remote Agent Experiment; and from 2002-2005 as a Technical Area Manager responsible for research in intelligent agents, software architecture, human-centered computing, search, collaborative knowledge management, distributed databases, information integration, spoken dialog systems, and the semantic web. Between 1998 and 2002, Dr. Pell worked in technical start-ups serving as Chief Strategist and Vice-President of Business Development at StockMaster.com, a provider of internet-based stock-market analysis tools and later Vice President of Strategy for Whizbang! Labs, a provider of advanced text processing and search engine software.

    Ron Kaplan,Ph.D., Chief Scientist, Powerset 
    Ronald M. Kaplan is Chief Scientific Officer at Powerset, Inc.  Prior to joining Powerset, he was a Research Fellow at the (Xerox) Palo Alto Research Center where he created and managed the Natural Language Theory and Technology research group. He is also a Consulting Professor in the Linguistics Department at Stanford University and a Principal of Stanford’s Center for the Study of Language and Information. He received his Ph.D. in Social Psychology from Harvard University, where he investigated how explicit computational models of grammar could be embedded in models of human language performance. He has made many contributions to computational linguistics and linguistic theory, and he has also provided linguistic technologies for commercial applications. He served as Chief Scientist of Microlytics, Inc. a PARC spin-off, and delivered software that was incorporated in products sold by Microlytics, Microsoft, Apple, Hewlett-Packard, Sony and other companies.  He served on the Technical Advisory Board of Inxight Software, another PARC spin-off that commercialized technology he developed. Kaplan is a past President of the Association for Computational Linguistics, a co-recipient of the 1992 Software System Award of the Association for Computing Machinery, and a Fellow of the ACM.  He has also been a Fellow-in-Residence at the Netherlands Institute for Advanced Study in the Humanities and Social Sciences.  He holds over 30 patents in computational linguistics and related areas.

    Rion Snow, PhD Candidate, Stanford University
    Rion Snow is a PhD Candidate in Computer Science at Stanford University working with Professors Andrew Ng and Dan Jurafsky.  Rion works in the intersection of machine learning and natural language processing, with a focus in computational semantics. He leads the Stanford Wordnet Project, which aims at learning large-scale semantic networks automatically from natural text. His work on automatically inferring semantic taxonomies recently received the Best Paper Award at the 2006 conference for the Association of Computational Linguistics.

    Location

    Cubberly Community Center
    4000 Middlefield Road, Room H-1
    Palo Alto, CA 94105
     

    Price

    $15 at the door for non-SDForum members
    No charge for SDForum members
    No registration required

    More on the Semantic Web SIG