• Open Archives: Communities, Interoperability, and Services (Fox)
  [abstract] [call for participation]
• Mathematical/Formal Methods in IR (Dominich, Lalmas, & van Rijsbergen)
  [abstract] [call for participation] [agenda: PDF version; MS Word version]
• Text Summarization (Harman & Marcu)
  [abstract] [call for participation] [agenda]
  
• IR Techniques for Speech Applications (Coden, Srinivasan, & Brown)
  [abstract] [call for participation] [agenda: PDF version; MS Word version]
• Operational Text Classification (Lewis, Dumais, Feldman, & Sebastiani)
  [abstract] [call for participation]
• Recommender Systems (Herlocker, Delgado, MacDonald, Oard, & Soboroff)
  [abstract] [call for participation]

Abstracts

Open Archives: Communities, Interoperability, and Services (Fox) Call for participation

The Open Archives Initiative (http://www.openarchives.org) develops and promotes standards that aim to facilitate the efficient dissemination of content regardless of the type of content offered. Its goal is to serve communities wishing to share information by ensuring interoperability and componentized, layered services. OAI was launched in October 1999 to provide a forum to discuss and solve problems of interoperability among author self-archiving solutions. OAI aims to support archives, both those focused on e-prints (e.g., theses and dissertations, Web log files, and educational resources). The emphasis has been on allowing harvesting of metadata that describes diverse "records" of content, stored in managed repositories. This workshop will allow those involved in the OAI, and those wishing to become involved, to extend the Initiative through sharing of technology, description and demonstration of services, and community-based discussion of conventions that ensure interoperability. The workshop will include an introduction to OAI and provide technology sharing and community building opportunities.

Mathematical/Formal Methods in IR (Dominish, Lalmas, & van Rijsbergen) Call for participation

The previous workshop (ACM SIGIR 2000 MF/IR 2000 Workshop, Athens, Greece) showed that the mathematical/formal results achieved in Information Retrieval (IR) could be organized into a coherent theoretical framework, that they brought new knowledge to IR, and that mathematical/formal research in IR can stand as a specialized research area of IR. The purpose of the MF/IR 2001 workshop is, on the one hand, to continue and enhance the results obtained so far, and on the other hand, to present, discuss, analyze, integrate the newer/newest results. Therefore, MF/IR 2001 aims at promoting discussion and interaction among those with theoretical and applicative research interests in mathematical/formal aspects of Information Retrieval, and also at being a forum for the presentation of both theoretical and applicative results (e.g., foundational issues; description and/or integration of models; retrieval applications; mathematical/formal techniques, properties and structures in IR; exigent and/or new theories and theoretical aspects).

Text Summarization (Harman & Marcu) Call for participation

Summarization technology has the potential of adding significant value in the context of information retrieval applications. Summarization can provide, for example, an alternative display mode for retrieved documents; a new method of concentrating information for relevance feedback; and a means for presenting information specific to groups of related documents and web sites. There has been a long history of research in this area by both the retrieval and the natural language processing communities, with summarization papers being presented at SIGIR and ACL. However we still do not know what summarization techniques are most adequate for which purposes and what evaluation techniques are most appropriate for assessing the quality of a summary. The purpose of this workshop is two-fold. The first day of the workshop will serve as a focal point for presenting new results in this area. This will include invited presentations focusing on various open problems in summarization research, presentations of original scientific papers, and an overview of the goals and results from a new evaluation effort in summarization called DUC (Document Understanding Conference, http://www-nlpir.nist.gov/projects/duc/). The optional second day of the workshop will be devoted to presenting more detailed results from the first DUC evaluation and to discussing plans for the future of DUC.

IR Techniques for Speech Applications (Coden, Srinivasan, & Brown) Call for participation

In the last few years automatic speech recognition has left the confines of the basic research lab and become a viable commercial application. Speech recognition technology has now matured to the point where speech can be used to interact with automated phone systems, control computer programs, and even create memos and documents. Moving beyond computer control and dictation, speech recognition has the potential to dramatically change the way we create, capture, and store knowledge. Advances in speech recognition technology combined with ever decreasing storage costs and processors that double in power every eighteen months have set the stage for a whole new era of applications that treat speech in the same way that we currently treat text. The goal of this workshop is to explore the technical issues involved in applying information retrieval and text analysis technologies in the new application domains enabled by automatic speech recognition. Specifically, we would like to focus on: 1) What new IR related applications, problems, or opportunities are created by effective, real-time speech recognition? 2) To what extent are information retrieval methods that work on perfect text applicable to imperfect speech recognition? 3) What additional data representations from a speech engine may be exploited by applications? 4) Does domain knowledge (context/voice-id) help and can it be automatically deduced? 5) Can some of the techniques explored be beneficial in a standard IR application? 6) What constraints are imposed by real time speech applications? 7) Case studies of specific speech applications - either successful or not.

Operational Text Classification (Lewis, Dumais, Feldman, & Sebastiani) Call for participation

Text classification research and practice has grown dramatically during the last decade. Text classification algorithms have been discussed at numerous conferences, but less is known about the issues that arise in deploying operational text classification systems. The goal of our workshop is to bring together practitioners and researchers to discuss these issues. Topics include the costs and benefits of text classification systems, system architecture, resource usage, maintaining and modifying of classifiers over time, integration of automated and manual procedures, combining of prior knowledge with machine learning, and so on.

Recommender Systems (Herlocker, Delgado, MacDonald, Oard, & Soboroff) Call for participation

Recommender systems assist and augment the transfer of recommendations among members of a community. Recommendations can describe content in a way that is complementary to keyword terms and to metadata. A typical system collects preferences and opinions from individual users, then aggregates and transfers those as recommendations to other members of the community. The goal of this workshop is to bring together researchers and practitioners involved in the development, analysis, and deployment of recommender systems. This workshop will provide a forum for discussing current and recent research results, and develop a road-map for future recommender systems research.