Ontolog invited Speaker Presentation - Dr. David Ferrucci - Thu 2006-05-11    (MDB)

Conference Call Details    (MDC)

Attendees    (MDU)

Agenda & Proceedings    (ME2)

http://ontolog.cim3.net/file/resource/presentation/DavidFerrucci_20060511/DavidFerrucci_20060511.png [picture of Dr. David Ferrucci]    (ME4)

Abstract: (by DavidFerrucci)    (ME5)

The dream of the semantic web as well as the future of information and knowledge management applications will rely on the rapid and massive explication of intended meaning (i.e., semantics) in unstructured information sources (e.g, text documents, video, speech etc). This talk will discuss the importance of embracing and deploying automatic semantic discovery, in spite of less that perfect accuracy, to help enable the semantic web, as well as an emerging class of advanced search applications we refer to a Knowledge Gathering and Synthesis applications. It will introduce IBM's recent contribution of UIMA (http://www.ibm.com/research/uima ) to the open-source community and discuss how this work will help accelerate the production and application of automated semantic discovery.    (ME6)

Dr. David Ferrucci is a Research Staff Member and Senior Manager at IBM’s T.J. Watson’s Research Center. He manages the Semantic Analysis and Integration department which is focused on technologies and architectures for discovering relevant knowledge in unstructured information and leveraging the results in a wide range of business intelligence and information management solutions. Principal research thrusts in his department include knowledge gathering and synthesis, automated question answering, semantic search, knowledge integration and the Unstructured Information Management Architecture (UIMA). His team includes world-class NLP, IR and Knowledge Representation researchers and software engineers. Dr. Ferrucci is the chief architect for UIMA (http://www.ibm.com/research/uima). This project provides the architectural and software foundation for accelerating and integrating a broad collection of efforts in advanced search, text and multi-modal analytics across six of IBM’s Research labs and several large government-sponsored projects. UIMA has become the standard platform for developing and delivering multi-modal analytics into IBM products and services aimed at solutions that help customers exploit the value in unstructured information sources. Its application outside of IBM, across research, industry and government is growing rapidly and helping to advance the science and application of text analytics. Throughout Dr. Ferrucci’s academic and professional career he has focused on designing computer systems to help people discover, represent, integrate, manage, and apply real-world knowledge. He is published in the field of logic and knowledge representation, architectures for natural language engineering, interactive document configuration, automated question answering and story generation. Dr. Ferrucci earned his PhD in computer science at Rensselaer Polytechnic Institute.    (MEE)

Session Recording of the DavidFerrucci Talk    (MEQ)

 (Thanks to KurtConrad, BobSmith and PeterYim for their help with getting the session recorded.  =ppy)    (MER)