Re: [unrev-II] faceted classification

From: John J. Deneen (jjdeneen@netzero.net)
Date: Fri Sep 28 2001 - 14:19:04 PDT

  • Next message: Jack Park: "[unrev-II] Orchard and Groves"

    See info about an intertesting classification rule and it's Noah
    algorithm at UCLA's CoBase-data mining project.

    "Cobase is an ongoing next-generation database project, developing
    techniques such as cooperative querying, temporal and spatial
    representations, and type abstraction hierarchies."
    < http://www.cobase.cs.ucla.edu/projects/datamining/ >
    < http://www.cobase.cs.ucla.edu/projects/datamining/Noah.htm >
    < http://www.cobase.cs.ucla.edu >

    Demo slides, including video clips
    < http://www.cobase.cs.ucla.edu/CoSenSlide >
    < http://www.cobase.cs.ucla.edu/Videos/part1.mov >
    < http://www.cobase.cs.ucla.edu/Videos/part2.mov >

    References, including
    "Semantic Data Modeling using XML Schemas"
    < http://www.cobase.cs.ucla.edu/tech-docs/dongwon/er2001.pdf >

    "Towards Intelligent Semantic Caching for Web Sources"
    < http://www.cobase.cs.ucla.edu/tech-docs/dongwon/jiis-645-00.pdf >

    These projects are under umbrella of the larger effort to build an
    intelligent information system in CoBae project supported by DARPA. The
    CoBase research group, aim is building a novel XML Query Processing and
    Relaxation system in Relational Storage. XPRESS stands for "Xml
    Processing and Relaxation in rElational Storage System"
    < http://www.cobase.cs.ucla.edu/projects/xpress/ >

    AN READ THIS:
    "Our associative query answering facility provides relevant information
    not explicitly requested in a user query. Case-Based Reasoning paradigm
    is employed to integrate previous experience to control the association.

    "The Case Memory consists of cases and association links. Cases are past
    user queries (e.g., Q1, Q2, Q3, or Q4). An association link (e.g., l1)
    is established by the attributes shared by the two cases (e.g., Q1, Q3),
    and the corresponding weight (e.g., w1), represents the usefulness of
    the association between the two cases. When a user query (Quser) is
    executed, its conditions, user type and context are compared against the
    Case Memory for similar cases (e.g., Q1 and Q2 are similar to Quser).
    Based on the set of similar cases, a set of association subjects (Q4 and
    Q3) can be selected through the traversal of association links (l2, l3,
    l4). The rank of an association is computed from the similarity measure
    of the corresponding case and the weights of the association links
    traversed. The ranking represents the usefulness of the case for the
    association. The cases with the high usefulness values (e.g., Q3 and Q4)
    are adapted into the user query, and provides associations to the user.
    Initially, the Case Memory has not acquired any experience. User
    feedback on the usefulness of the associations is incrementally
    integrated into the Case Memory, thus, the weights of the association
    links traversed are adjusted. In this way, the Case Memory can
    accumulate experience and improve the associations from the user
    feedback."
    < http://www.cobase.cs.ucla.edu/arch.html#association_mediator >

    Also, it's sister project Knowledge-Based Multimedia Medical Distributed
    Database System (KMeD).
    < http://www.kmed.cs.ucla.edu/>

    Alex Shapiro wrote:

    > At 12:11 PM 9/28/01 -0400, you wrote:
    >
    >> At 04:36 PM 9/28/01 +0100, you wrote:
    >>
    >> > Faceted classification sounds a lot like the sort of feature
    >> > definition that
    >> > gets done when defining cases in case-based reasoning, and even
    >> > like plain
    >> > old fashioned relational databases. (Or did I miss the point?) If
    >> > so
    >> > experience in these fields might give pointers on how to do it
    >> > well.
    >> >
    >> > Dr Victoria Uren
    >> > KMi, Open University, Milton Keynes, MK7 6AA, UK
    >> > Tel: +44 (0) 1908 858516
    >> > http://kmi.open.ac.uk/people/victoria/
    >> > http://kmi.open.ac.uk/projects/scholonto/
    >>
    >> And saying that something can be placed into a database does miss
    >> the point (I think). Lots of data structures could be placed into a
    >> database. The interesting thing is how the structure maps to the
    >> data, not how the structure could be represented in a database.
    >>
    >> --Alex
    >
    >
    > Then again, there are similarities between the structure of a
    > relational database, and the structure represented by faceted
    > classification. Here is a quote I found from the same source as the
    > last link:
    > http://www.slais.ubc.ca/courses/libr517/winter2000/Group7/database.htm
    >
    > "If one considers the development of models of database designs and
    > the development of classification schemes, one may notice a parallel
    > between the two, moving from a more hierarchial structure to a faceted
    > one. Relational databases have replaced the older hierarchial
    > databases, and are found to be more effective in organizing data. "
    >
    > Also, I checked out the ScholOnto project and I am very impressed. I
    > especially like the goals outlined in section 4.2 of this paper:
    > "ScholOnto: An Ontology-Based Digital Library Server for Research
    > Documents and Discourse"
    > http://kmi.open.ac.uk/projects/scholonto/docs/ScholOnto-IJoDL-2000.pdf
    >
    > I think that the approach taken for creating a semantic network from
    > existing publications is right on target.
    >
    > What seems a little strange to me, is ScholOnto's goal of facilitating
    > discussions about the scholarly works, while at the same time
    > diagramming the works being discussed. It seems that creating
    > semantic maps out of existing documents, and facilitating graphical
    > discussions are distinct enough tasks to deserve separate
    > applications. For instance, I could imagine an independent forum
    > where scholarly papers are discussed, and where one could post links
    > to existing papers. Such a forum would certainly benefit from a back
    > end where the scientific papers are also diagrammed, but it would not
    > require it.
    >
    > Regardless though, I am very impressed with the project, and look
    > forward to reading the rest of your publications.
    >
    > --Alex
    > Yahoo! Groups Sponsor
                            ADVERTISEMENT
                                [Image]

    >
    > Community email addresses:
    > Post message: unrev-II@onelist.com
    > Subscribe: unrev-II-subscribe@onelist.com
    > Unsubscribe: unrev-II-unsubscribe@onelist.com
    > List owner: unrev-II-owner@onelist.com
    >
    > Shortcut URL to this page:
    > http://www.onelist.com/community/unrev-II
    >
    > Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.



    This archive was generated by hypermail 2.0.0 : Fri Sep 28 2001 - 14:09:02 PDT