ontology-enhanced retrieval (and ontology-enhanced applications)

Download Ontology-enhanced retrieval (and Ontology-enhanced applications)

Post on 17-Jan-2016

35 views

Category:

Documents

2 download

Embed Size (px)

DESCRIPTION

Ontology-enhanced retrieval (and Ontology-enhanced applications). Deborah L. McGuinness Associate Director and Senior Research Scientist Knowledge Systems Laboratory Stanford University Stanford, CA 94305 650-723-9770 dlm@ksl.stanford.edu - PowerPoint PPT Presentation

TRANSCRIPT

  • Ontology-enhanced retrieval (and Ontology-enhanced applications)Deborah L. McGuinnessAssociate Director and Senior Research ScientistKnowledge Systems LaboratoryStanford UniversityStanford, CA 94305650-723-9770 dlm@ksl.stanford.edu

    (FindUR,CLASSIC,PROSE work supported by AT&T Labs Research, Florham Park, NJ, OntoBuilder work supported by VerticalNet,Chimaera, Ontolingua, JTP supported by DARPA)

  • One Conceptual SearchInput is in a natural query language (forms, English, ER diagram )Query may be transformed (behind the scenes) into a precise query language with defined semanticsInformation is at least semi-structured with DL-like markup and also exists in more natural formats and is interoperableAnswers returned that are not just the explicit answer to question (but also the implicit answer to question)Answers return the portion of the content that is of use (not an entire page of content)Answers may be summarized, abstracted, prunedAnswers may be services that can take actionInterface is interactive and helps users reformulate unsuccessful queriesCustomizable, extensible,

  • Today: Rich Information Source for Human Manipulation/Interpretation

  • I know what was inputGlobal documents and terms indexed and available for searchSearch engine interfacesEntire documents retrieved according to relevance (instead of answers)Human input, review, assimilation, integration, action, etc.Special purpose interfaces required for user friendly applications

    The web knows what was input but does little interpretation, manipulation, integration, and action

  • Information Discovery but not much moreHuman intensive (requiring input reformulation and interpretation)Display intensive (requiring filtering)Not interoperableNot agent-operationalNot adaptiveLimited contextLimited service

    Analogous to a new assistant who is thorough yet lacks common sense, context, and adaptability

  • Future: Rich Information Source for Agent Manipulation/Interpretation

  • I know what was meantUnderstand term meaning and user backgroundInteroperable (can translate between applications)Programmable (thus agent operational)Explainable (thus maintains context and can adapt)Capable of filtering (thus limiting display and human intervention requirements)Capable of executing services

  • One Approach start simple from embedded basesRecognize the vast amount of information in textual formsEnhance standard information retrieval by adding some semantics Use background ontology to do query expansionExploit ontology to add some structure to IR searchMove to parametric searchMove to include inference (in e-commerce setting moving towards interoperable solutions and configuration

  • FindUR Challenges/BenefitsRetrieve documents otherwise missed - RecallMore appropriately organize documents according to relevance (useful for large number of retrievals)Browsing support (navigation, highlighting)Simple User Query building and refinement Full Query Logging and TraceFacilitate use of advanced search functions without requiring knowledge of a search language Automatically search the right knowledge sources according to information about the context of the query

  • (FindUR ArchitectureSearchEngineContent to Search:Search and Representation Technology:User Interface:Verity Topic SetsContent (WebPages, Documents, Databases)Results(domain spec.)Verity SearchScript, Javascript, HTML, CGIContentClassificationDomainKnowledgeResults(std. format)SearchParameters ClassicCollaborative Topic Building ToolQuery InputP-CHIPResearch SiteTechnical MemorandumCalendars (Summit 2005, Research) Yellow Pages (Directory Westfield)Newspapers (Leader) AT&T SolutionsWorldnet Customer Care

  • OntologyBuilder

  • Configurationhttp://www.research.att.com/sw/tools/classic/tm/ijcai-95-with-scenario.html

  • Ontology Creation and Maintenance Environment NeedsSemi-automatic generation inputDiagnostics/Explanation (Chimaera, CLASSIC,)Merging and Difference (Chimaera, Prompt, Ontolingua, )Translators/Dumping (Ontolingua, )Distributed Multi-User Collaboration (OntologyBuilder,)Versioning (OntologyBuilder,)Scalability. Reliability, Performance, Availability (Shoe,OntologyBuilder,)Security (viewing, updates, abstraction, authoritative sources)Ontology Library systems (Ontolingua,)Business needs internationalization, compatibility with standards (XML,)

  • ConclusionWith background ontologies and the appropriate environments, we can move from simple ontology-enhanced applications to the next generation web

  • PointersFindUR: www.research.att.com/~dlm/findurOntoBuilder/OntoServer: http://www.ksl.stanford.edu/people/dlm/papers/ontologyBuilderVerticalNet-abstract.htmlDeborah McGuinness: www.ksl.stanford.edu/people/dlmCLASSIC: www.research.att.com/sw/tools/classicChimaera: www.ksl.stanford.edu/software/chimaera/

    The web is an amazing resource which is growing at an astounding rate. It is clearly changing our lives and will continue to do so. It is a rich information source

Recommended

View more >