1 / 8

Vipul Kashyap ( kashyap@nlm.nih ) National Library of Medicine, NIH September 1, 2003

Vipul Kashyap ( kashyap@nlm.nih.gov ) National Library of Medicine, NIH September 1, 2003 Workshop on Data Quality, Dagstuhl, Germany. Trust and Quality for Information Integration: The Data-Metadata-Ontology Continuum. The Importance of Quality of Information and Trust.

quade
Download Presentation

Vipul Kashyap ( kashyap@nlm.nih ) National Library of Medicine, NIH September 1, 2003

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Vipul Kashyap (kashyap@nlm.nih.gov) National Library of Medicine, NIH September 1, 2003 Workshop on Data Quality, Dagstuhl, Germany Trust and Quality for Information Integration: The Data-Metadata-Ontology Continuum

  2. The Importance of Quality of Information and Trust

  3. * Thanks to Gunther Eysenbach

  4. Semantic Web: Information Aspects Ontological-terms (Domain, Application specific) Vocabulary used-by used-by Metadata Content (content descriptions, intensional) abstracted-into abstracted-into Data Representation (heterogeneous types, media)

  5. Role of Trust and Quality in Information Retrieval and Integration • Data Quality • Is this information source reliable, trustworthy? • Does a particular information source have better quality of data? • Impacts: • Entity matching and identification (Information Retrieval) • Record and ID matching (Information Integration) • Resolution of conflicting information • Relationship between DQ and DT • Is DQ = f(DT) • Or Trust = f(DQ) ? • Or is there some notion of fixpoint computation? • Relationship between the results and data quality • Answer = f(DT, DQ) ? • Do these parameters induce a ranking on the set of results?

  6. Role of Trust and Quality in Information Retrieval and Integration • Metadata Quality (MQ) and Metadata Trust (MT) • Trust/Reliability of metadata exported by information sources • Trust/Reliability of mappings/morphisms exported by the information source • Introduction of new dimensions into the equation: • MQ = f(DQ, MT) ? • MT = f(DT, MQ) ? • MQ and internal consistency • Are the mappings internally consistent with each other? • Use of category theory based structures? • Formalism to provide a mathematical basis for data quality?

  7. Role of Trust and Quality in Information Retrieval and Integration • Ontology Quality (OQ) • Structural Quality of the ontology • Notion of semantic richness • Notion of internal consistency (no contradictions) • Notion of completeness of domain coverage • “Atomic Quality” of the ontology: more directly correlated with Ontological Trust (OT) • Quality of concepts and relationships • Quality of axioms and contraints (for semantically rich ontologies) • Notion of “Ontological commitments” • OQ = f(Structural Quality) • Employ graph-based comparison approaches • OT = f(Atomic Quality) • Investigate “cultural” consensus analysis approaches

  8. Role of Trust and Quality in Information Retrieval and Integration • The Goal: • Identify and formalize interrelationships between the following dimensions • DQ/DT • MQ/MT • OQ/OT • Is it generalizable beyond information retrieval and integration? • Build on existing information retrieval and integration research • Evalution of End-to-End Impact • Quality/Trust of answers • f(DQ, DT, MQ, MT, OQ, OT) ? • Ranking of answers

More Related