Searching Indexed Databases versus Text Mining – The battle between „traditional“ added-value databases and information extraction from full-text Dr. Wolfgang Thielemann, Head of Information Retrieval; Patent, Literature & Competitor Information, Bayer Healthcare AG
Abstract:
Added value databases have been available for decades and they still are the most frequently used resource for information professionals. Although the indices, searching functionality and analysis options of these databases have been constantly improved, new technologies, and text mining in particular, promise to deliver the same or even a higher level of information from unstructured text. Is text mining now or will it ever be a replacement for indexed databases? Can an automatic or semi-automatic mining process match an experienced indexer with regard to grapping the essence of news, publications or patents? And what is the role of the information professionals when using text mining; do they have to learn more about technology or the structure of the sources or are they themselves going to be replaced like the indexer? This talk will focus on the strengths and weaknesses of both technologies from the perspective of an information professional who has been using both approaches for several years within a pharmaceutical company.
Biography:
Wolfgang Thielemann is currently managing the Information Retrieval Group of Bayer HealthCare. After receiving his Ph.D. in Organic Chemistry from the University of Münster, Germany in 1997 he spend a year as postdoctoral fellow in the Group of Prof. Paul Bartlett at the University of California, Berkeley. In 1999 he started as a medicinal chemist in the Chemical Research Department of Bayer Pharma. After 3 years of chemical research he moved to the Scientific Information and Documentation department as head of the patent information group. In 2004 he received the Bayer Pharma Research Award for the development and establishment of Patent Mining. With the beginning of 2005 he became head of the information retrieval group which is responsible for retrieval and analysis of patent, literature, competitor and business information for customers within Bayer HealthCare.