Tutorial Choice(s): Please indicate choice(s)

Morning Tutorials (September 9, 2001, 8:30-12:30)

• Introduction to Information Retrieval (Mark Sanderson, University of Sheffield)
  Introduces the core concepts of Information Retrieval and provides attendees with extensive bibliographic information to allow them to pursue their interests further.
• Web Information Retrieval (Krishna Bharat, Google, Inc. and David Hawking, CSIRO Canberra)
  Intends to bring researchers, students and practitioners up to speed with both the theory and practice of Web search. Based on an understanding of challenges specific to the Web collection and user base, it will explore the state of the art in algorithms, deployment infrastructure and evaluation methodology. Participants will have basic familiarity with the Web and search engines, and exposure to IR concepts such as ranked retrieval and test collections.
• Multilingual Information Access (Carol Peters, IEI-CNR, Italy and Paraic Sheridan, MNIS- TextWise Labs)
  Provides an exhaustive overview and includes introductory material, a review of issues in multilingual text processing, techniques for cross-language text retrieval, evaluation of cross-language retrieval systems, and a study of some existing systems.
• Text Summarization (Dragomir Radev, University of Michigan)
  Focuses on established and emerging techniques for producing automated summaries of text. The expected audience includes researchers and graduate students with interests in Information Retrieval and Natural Language Processing.

Afternoon Tutorials (September 9, 2001, 1:30-5:30)

• Combining Text- and Link-Based Information Retrieval on the Web (Andrei Broder, Altavista) and Prabhakar Raghavan, Verity)
  Reviews the development of combined text and link-based retrieval, classification and clustering methods and examines what insights from web IR can (and cannot) be abstracted back into enterprise settings. The tutorial is for researchers, students and professionals seeking an understanding of the similarities and differences between web and enterprise information retrieval, and it complements to the one by Bharat and Hawking.
• Text Classification and Text mining in vivo (David Lewis, Independent Consultant)
  Introduces practitioners and researchers to applications of text classification and related techniques that have emerged in text mining. The tutorial focuses on the priorities and constraints encountered in fielding this technology in operational settings. While it emphasizes automated approaches (particularly machine learning), it also discusses the tradeoffs between automated and more human-intensive methods.
• Designing Information Architectures for Search (Marti Hearst, Univ. California, Berkeley)
  Introduces and explains a systematic approach to designing information architecture for web sites consisting of large collections of related information with the goals of producing websites with multiple different views to reflect differences in user's preferred search and browsing methods, and incorporating search uniformly throughout the design of the site.
• Practical Digital Libraries Overview (Ed Fox, Virginia Polytechnic University)
  Covers a variety of issues, including search, retrieval and resource discovery; multimedia/hypermedia; metadata (e.g., Dublin Core); electronic publishing; document models and representations; SGML and XML; database approaches; agents and distributed processing; 2D and 3D interfaces and visualizations; metrics; architectures and interoperability (e.g., OAI); commerce; educational (e.g., CSTC, NSDL, NDLTD) and social concerns; and intellectual property rights.