Referent

Jo van Nouhuys
Michael R. Alvers,
Geschäftsführer, Transinsight GmbH

Titel:
Knowledge Based Search – Towards Finding answers

Abstract:
"Does the world really need another search engine?" Our answer is YES. Why? Because today’s search technology is in it’s very early stadium. Full text search for words fails miserably when it comes to more complex topics like biomedical research. The key for enabling search machines to communicate with the searchers is the intelligent usage of knowledge.

GoPubMed is a Biomedical search engine which uses background knowledge in form of Ontologies for searches and leads faster to much better search results. The estimated time savings for knowledge searches are at least 50%.

GoPubMed is able to retrieve MEDLINE abstracts for the search query. Using novel award winning text mining methods for automated recognition of concepts GoPubMed detect terms from the Gene Ontology (GO) and Medical Subject Headings (MeSH) in the abstracts, display the subset of the GO and MeSH relevant to the keywords, and allow you to browse the ontologies and display only papers containing specific GO and MeSH terms. The hierarchies can be used to systematically explore the search results. Results are hierarchically classified in „WHAT“, „WHO“, „WHERE“ and „WHEN“ categories using text mining methods.

Sorting documents to a highly organised network facilitates the finding of relevant documents significantly. „WHAT“, „WHO“, „WHERE“ and „WHEN“ serve as table of contents in order to structure the millions of articles of the MEDLINE data base.


Zurück