W3C home > Mailing lists > Public > public-owl-wg@w3.org > October 2007

RE: Introductions

From: Kashyap, Vipul <VKASHYAP1@PARTNERS.ORG>
Date: Wed, 10 Oct 2007 14:07:43 -0400
Message-ID: <DBA3C02EAD0DC14BBB667C345EE2D124010F00CB@PHSXMB20.partners.org>
To: <public-owl-wg@w3.org>


My name is Vipul Kashyap and I have been some sort of a semantics

junkie/evangelist/believer right since the early days of my career as a computer
scientist. Though metadata, semantics and ontology-based approaches are
currently gaining steam, various researchers have been working along these lines
for a long time. Some systems which I have been associated with are:


The InfoHarness system, (with Amit Sheth and Leon Shklar) developed at Bellcore
(now known as Telcordia) was a metadata-driven system for logically
restructuring the information space. GeoLens
(http://www.argreenhouse.com/geolens), VisualHarness and commercial products

such as Adept X/Harness, SmartCode/Metaphoria were built on top of this


The OBSERVER system (http://sid.cps.unizar.es/OBSERVER) (with Eduardo Mena)

demonstrated the use of independently developed ontologies (based on WordNet) to
interrogate independently developed data repositories (e.g., the Library of
Congress and the Library of Monterrey) storing information using 

different formats (e.g., MARC records) and supporting different information

access protocols (Z39.50). This was one of the earliest systems that used
Description Logics (like OWL-DL) for information integration and retrieval.


The InfoSleuth system (http://www.argreenhouse.com/InfoSleuth) demonstrated the
use of ontology and semantics-aware agent communities for information gathering
and analysis. I worked on the ontology agent that used OKBC protocol and KIF as
the interchange language for expressing ontologies.


The TaxaMiner system (http://lsdis.cs.uga.edu/~cartic/taxaminer.htm)

demonstrated the use of NLP and statistical techniques to bootstrap rough
ontologies from medical research articles from PubMed. We were

able to generate ontologies that approximated MeSH to a large extent.


My experiments and adventures with semantics made it clear to me that nowhere is
the need and alignment with semantics so clear as with the HealthCare and Life
Sciences information! And besides, Biomedicine has been one of the earliest
users of semantics, courtesy, the Linneas Binomial

Classification of species !!! This led me to a two year Research Fellowship at
the National Library of Medicine after which I joined Partners HealthCare System
as a Senior Medical Informatician.


At Partners Healthcare, we are currently evaluating semantic web specifications
and technologies such as OWL and RDF for clinical decision support, impact
analysis and change management. We look forward to contribute use cases from the
Healthcare and Life Sciences and help define a robust and pragmatically usable
OWL 1.1 specifications that support our use cases and requirements. To this end,
I am currently leading a task force on Clinical Observations Interoperability
that is exploring semantic web based approaches for interoperation between EMRs
and Clinical Trial Systems.




Look forward to working with you folks. Let's reach out for the chips, salsa and
beer ...

Let the party begin ... !!!


Semantically yours,


---Vipul Kashyap



Vipul Kashyap, Ph.D.

Senior Medical Informatician

Clinical Informatics R&D, Partners HealthCare System

Phone: (781)416-9254

Cell: (617)943-7120



To keep up you need the right answers; to get ahead you need the right questions

---John Browning and Spencer Reiss, Wired 6.04.95

The information transmitted in this electronic communication is intended only for the person or entity to whom it is addressed and may contain confidential and/or privileged material. Any review, retransmission, dissemination or other use of or taking of any action in reliance upon this information by persons or entities other than the intended recipient is prohibited. If you received this information in error, please contact the Compliance HelpLine at 800-856-1983 and properly dispose of this information.
Received on Wednesday, 10 October 2007 18:08:02 UTC

This archive was generated by hypermail 2.3.1 : Tuesday, 6 January 2015 21:41:59 UTC