W. Bruce Croft, PI
Center for Intelligent Information Retrieval (CIIR)
University of Massachusetts Amherst
Matthew Koll, Co-PI
R. David Lankes, Co-PI
Information Institute of Syracuse University (IIS)
The CIIR, under the direction of Professor Bruce Croft, is partnering with the Information Institute of Syracuse University (IIS) and the Wondir Foundation to enhance the NSDL by merging the information retrieval (IR) and digital reference components. By combining these functions, users can find answers to their questions regardless if those answers come from documents in NSDL collections or experts accessible through the NSDL's virtual reference desk.
The combination of IR and digital reference provides powerful possibilities, with each field complementing the other. In terms of IR, experts and human intermediation developed in digital reference can handle questions currently beyond the scope of the IR system, or even the collection being searched. The technical focus is to develop techniques for query triage, a process where queries will be automatically routed to the appropriate IR or human resource. This research will involve the application of machine learning and language modeling techniques to large query logs collected in an operational environment.
The CIIR's partners provide broad experience to the project. The Information Institute of Syracuse (IIS) is the umbrella organization for a number of highly visible and widely successful digital education information services. The IIS administers and sponsors the ERIC Clearinghouse on Information & Technology and related projects for educators at all levels including the award-winning, Internet-based AskERIC question and answer service. The Wondir Foundation's mission is to provide a free, universal, integrated, independent and unbiased search service, combining search and community in ways possible only in a nonprofit organization. Wondir will combine Search and Community-two pillars of the Internet that have not yet lived up to their potential-by offering the instant help of the millions of experts and enthusiasts online at any one time, along with a broad metasearch of web sources and valuable "invisible" web resources.
This work was supported in part by the Center for Intelligent Information Retrieval (CIIR) and in part by the National Science Foundation grant number DUE-0226144.