1 / 28

Second Presentation

Second Presentation. Michael Belanger, Cofounder, Jarg Corporation and it’s SemanTx Life Sciences div. URLS to OPEN (and minimize ):. http://www.cmch.tv/research/. http://gw.jarg.com/jsp/index.jsp. First Key take-away Point

tacy
Télécharger la présentation

Second Presentation

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. Second Presentation Michael Belanger, Cofounder, Jarg Corporation and it’s SemanTx Life Sciences div. URLS to OPEN (and minimize): http://www.cmch.tv/research/ http://gw.jarg.com/jsp/index.jsp

  2. First Key take-away Point Bioinformatics and life sciences areas are ahead in implementation of semantic standards and technologies. The Federal Semantic Enterprise Implementation as well as other fields can now benefit from that ontology-based computing investment and experience.

  3. Second Key take-away Point How many different terms from how many different fields can mean the same “concept” ?

  4. Located at Children’s Hospital Boston

  5. Just One Professional Field

  6. The CMCH SemanTx ontology mediates the disparate vocabulary of 10 professional fields that media research is occurring in:  medicine, psychology, education, anthropology, public health, communication, criminology, gender studies, social work sociology.

  7. Third Key take-away Point Using the Semantic Knowledge Indexing Platform (SKIP) there is no limitation as to how many different terms, XML tags, Jargon or other metadata from different fields that can be expressed to mean the same “concept”

  8. Currently a few thousand media-related research abstracts are being searched

  9. measures “SemanTx” Abstraction From Both The Info Source and The Query Development of an Assay for Eukaryotic Telomeric Recombination development eukaryotic produces • Telomeres, the physical ends of chromosomes, are essential for maintaining chromosome stability and structure. The mechanisms that maintain the simple sequences present at the telomere within a discrete distribution is poorly understood. One such mechanisms, termed rapid deletion events (RPD) has been described in our laboratory to occur frequently in Saccha- assay telomeric eukaryote is_a Is_a property_of test recombination telomere cell location_of Is_a chromosome process Ontology’s Query Expansion From “Institutional” Knowledge

  10. Process Overview & Advantages • Answers returned, ranked by contextualrelevance • Allows for cross-disciplinary research to shorten discovery & response cycles Step 1: Enter query in plain English Step 3: Review highlighted contextual answer within document Step 2: Proves match results

  11. Understands - as a “Graph” “Why” This Ranking!

  12. Forth Key take-away Point The more context you articulate in your query, the more precision in your results Returns have been context-matched and then ordered by how well the meaning within sources matches the meaning expressed in your query Why is this better and different from other search architectures?

  13. Ranked By Fit-To Context Quigo(categorization) Clearforest Entity Extraction Verity, Convera, Endeca Inxight, Fast Taxonomy iPhrase Syntactic Yahoo Directory Pattern Match Google Cluster MSN Word Match/Key Words Bottom-Up Filtering Top-Down Semantic Results ordered by best fit-to-context “SKIP” Serves-UpWell-Articulated results ! Domain Ontology’s Contextual Meaning Autonomy Search Today

  14. Boston Children’s Hospital CMCH – SemanTx “Smart Search” More Contextual Query Ideas for you to try: Should reading and television together be encouraged? Do video games affect children's learning abilities? What is the impact of the media on adolescent sexual attitudes and behaviors? Does TV cause ADHD? Do language tapes help children talk? Can parents prevent children from experiencing unwanted effects of violent television programs? Does watching TV lead to obesity? “Articulate” Your Own Context-Filled Queries at: http://www.cmch.tv/research/

  15. An Example of: Immediate “Learning Curve” Transfer E-Government “controlled” Metadata Tagging mandates? Need to append “official” cross-government meta-tags to all your e-mails and documents? Problem Solved - (Children’s Hospital Boston) Semantic “Abstractions” of Content Overcomes Social Issues ********************************** Rapid Employee Turnover ? Critical Employees Retiring ? High Value Consultants Gone ? Scalable Pilot Installation Bio-medical-environmental related department < $25k E-GDpt X X X X X X

  16. Addressing items 2 & 3 for today: Brand Niemann did “try us” and typed-in the SICoP “challenge query’ into Jarg Corporation’s Semantic Life Sciences Division’s Semantic PubMed site: http://gw.jarg.com/jsp/index.jsp and saw relevant results. “Essentially, you have come the closest to meeting the semantic query challenge we featured in the SICoP Module 1 White Paper!”

  17. Jarg Corporation’s Semantic Life Sciences Division’s Semantic PubMed site http://gw.jarg.com/jsp/index.jsp

  18. Need to searching millions of data files? There is no limit to the number of indexed databases - no performance penalties with SKIP “Articulate” your need with lots of Context

  19. Your query “abstracted” as a graph Click - to MedLine

  20. Mass General Lab’s Paper

  21. Many Joins

  22. Only 2 Joins Mass General Missing

  23. Term Synonym Found Mass General Lost the others

  24. Fifth Key take-away Points From All Ontology-Parsed Object Types – SKIP Enables Effective Achievement of Both: Excellent Semantic Precision & Excellent Semantic Recall Due to “fit-to-context” Search Results

  25. Filtering Objects By Their Content’s MeaningA Fresh, Scalable, High Performance Approach • Sub-Ontology based semantic object-parsing • Enables capture of context for the extraction of “understood features” from within all forms of information to be “semantically represented” then indexed in SKIP’s common semantic (“fragment”) format • Semantically-rich (complex queries) express the context of your need • Return a “collage” of rich-media results • Each result prioritized by its contextual fit to a user’s expressed query

  26. High Performance Knowledge Interoperability Semantic Knowledge Indexing Platform (SKIP) Multimedia’s “Native Content” & Geospatial Search Semantic Queries and SW Agent Alerts Ontologies Unified “Content Awareness” Across The Federal Enterprise Core Base Search & Retrieval Your Portal Ontologies Dynamic Situation-Awareness, SW Agent-based Alerts Unique-Identifier Combined Index Ontologies

  27. Your Semantic Indexing & Search Collaborator • SemanTx Life Sciences Seeks Semantic Search • Collaborative / Licensing Partners • Effective Semantic Use of large Ontologies (UMLS) • Effective Achievement of Both Excellent Semantic Precision & Semantic Recall of Search Results • Effective High-scale & High Performance (Google-like) Search Architecture • Life Science Applications - as “Operational” Examples for Fast Adoption for: • FEA Semantic Interoperable Search & Retrieval Platform • Concept and Word, non-intrusive, “Abstraction From” New • e-Mail/Docs, to match / “check-off-Append” of “Official” Cross-FEA Meta Tags • Communities of Interest – rapid deployment - Collaborations in: • Avian Flu Pandemicor Environmental Toxinthreats • Early detection of developing medical disaster recovery problems • Early detection of developing bio/medical terrorist threats • Contact: mpbelanger@semantxls.comThank you

More Related