Ontology-enhanced retrieval (and Ontology-enhanced applications)

1
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_at_ksl.stanford.edu
• (FindUR,CLASSIC,PROSE work supported by ATT Labs
  Research, Florham Park, NJ, OntoBuilder work
  supported by VerticalNet,
• Chimaera, Ontolingua, JTP supported by DARPA)

2
One Conceptual Search

• Input is in a natural query language (forms,
  English, ER diagram )
• Query may be transformed (behind the scenes) into
  a precise query language with defined semantics
• Information is at least semi-structured with
  DL-like markup and also exists in more natural
  formats and is interoperable
• Answers 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, pruned
• Answers may be services that can take action
• Interface is interactive and helps users
  reformulate unsuccessful queries
• Customizable, extensible,

3
Today Rich Information Source for Human
Manipulation/Interpretation
4
I know what was input

• Global documents and terms indexed and available
  for search
• Search engine interfaces
• Entire 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

5
Information Discovery but not much more

• Human intensive (requiring input reformulation
  and interpretation)
• Display intensive (requiring filtering)
• Not interoperable
• Not agent-operational
• Not adaptive
• Limited context
• Limited service
• Analogous to a new assistant who is thorough yet
  lacks common sense, context, and adaptability

6
Future Rich Information Source for Agent
Manipulation/Interpretation
7
I know what was meant

• Understand term meaning and user background
• Interoperable (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

8
One Approach start simple from embedded bases

• Recognize the vast amount of information in
  textual forms
• Enhance standard information retrieval by
  adding some semantics
• Use background ontology to do query expansion
• Exploit ontology to add some structure to IR
  search
• Move to parametric search
• Move to include inference (in e-commerce setting
  moving towards interoperable solutions and
  configuration

9
FindUR Challenges/Benefits

• Retrieve documents otherwise missed - Recall
• More 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 Trace
• Facilitate 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

10
FindUR Architecture
P-CHIP Research Site Technical Memorandum Calendar
s (Summit 2005, Research)
Yellow Pages (Directory Westfield) Newspapers
(Leader) ATT Solutions Worldnet Customer
Care
(
Content (Web Pages, Documents, Databases)
Content to Search
Content Classification
Search Engine
Search and Representation Technology
Classic
Collaborative Topic Building Tool
Domain Knowledge
User Interface
Search Parameters
Query Input
Verity Topic Sets
Verity SearchScript, Javascript, HTML, CGI
Results (domain spec.)
Results (std. format)
11
(No Transcript)
12
(No Transcript)
13
(No Transcript)
14
(No Transcript)
15
OntologyBuilder
16
Configuration
http//www.research.att.com/sw/tools/classic/tm/ij
cai-95-with-scenario.html
17
Ontology Creation and Maintenance Environment
Needs

• Semi-automatic generation input
• Diagnostics/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,)

18
Conclusion

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

19
Pointers

• FindUR www.research.att.com/dlm/findur
• OntoBuilder/OntoServer http//www.ksl.stanford.ed
  u/people/dlm/papers/ontologyBuilderVerticalNet-abs
  tract.html
• Deborah McGuinness www.ksl.stanford.edu/people/d
  lm
• CLASSIC www.research.att.com/sw/tools/classic
• Chimaera www.ksl.stanford.edu/software/chimaera/