WWW 2008 / Workshop Summary April 21-25, 2008 · Beijing, China International Workshop on Question Answering on the Web (QAWeb2008) Liu Wenyin Dept of Computer Science City University of Hong Kong 83 Tat Chee Ave. KLN, Hong Kong +852-2784-4730 Qing Li Dept of Computer Science City University of Hong Kong 83 Tat Chee Ave. KLN, Hong Kong +852-2788-9695 Xuedong Huang Microsoft Corporation One Microsoft Way Redmond WA, 98052-6399, USA +1-425-706-2966 csliuwy@cityu.edu.hk ABSTRACT itqli@cityu.edu.hk xdh@microsoft.com A half-day single track workshop is designed to gather academic researchers and industrial practitioners at to share ideas and knowledge of know-how, and to discuss all relevant issues including the business models, enabling technologies, and killer applications, of Web-based question answering (QA), especially, the user-interactive QA services and applications. The workshop program consists of two sessions, one for academic papers, and the other for industrial practice papers. Each session consists of a leading talk, followed by three short presentations. Sufficient time is allocated for brainstorming discussions in each session. practitioners at all level of experience to share ideas and knowledge of know-how, and to discuss all relevant issues including the business models, enabling technologies, and killer applications, of QA, especially InterQA. We expect all participants to actively participate in the panel discussions in addition to the academic and practice paper presentations. A summary of the brainstorming panel discussion at each session will be published on the workshop website [2], together with all the presented papers. We wish the summaries can inspire more research output and fruitful applications. Categories and Subject Descriptors H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval. 2. THEMES AND TOPICS All topics related to question answering (QA), especially, userinteractive QA, are of interest for the Workshop. These topics include but are not limited to: System Architecture, Algorithms, User Interfaces, Business Models, User Models and Personalized Recommendation, Question Categorization, Answer Clustering, Answer Fusion, Social Networks, Reputation Models, Text Similarity, Short Text Modeling, Patterns and Semantic Patterns, Performance Evaluation, and Applications. General Terms: Algorithms, Design, Experimentation, Human Factors, Languages, Performance, Standardization. Keywords: Question Answering. 1. OBJECTIVES Question answering (QA) is an emerging new information service following the popularization of search engines. QA can be more preferable since a direct and exact answer is expected instead of a long list of ranked, possibly relevant but usually long documents, which can be automatically returned by a search engine but still require the user's manual and sometimes very tedious filtration. After a decade of constant research efforts, we are seeing that automatic question answering (AutoQA) has grown up into a new and hot sub-area of information retrieval. However, userinteractive question answering (InterQA) which just emerged a couple of years ago has already witnessed its milestone of being mature and successful since 2007. For example, Yahoo! Answers [1] was ranked as the best Web 2.0 service in 2007. We are anticipating a new wave of hot Web information services based on InterQA since it is a natural complement to search engines, or alternatively, can be considered as manual search engines. Although AutoQA has been discussed by TREC, CLEF, SIGIR and NTCIR as a sub-domain for many years, we'd like to dedicate a single mind event to discuss all issues of QA. Therefore, we propose to start QAWeb2008 as the beginning of a new series of workshops, which will gather academic researchers and industrial Copyright is held by the author/owner(s). WWW 2008, April 21­25, 2008, Beijing, China. ACM 978-1-60558-085-2/08/04. 3. PROGRAM The program consists for two sessions, one for academic paper presentations and the other for presentations of papers with industrial practices and experiences. Each session consists of a lead talk (30 minutes) followed by three short presentations. In addition, a lead talk may use about 10-15 minutes to cover a brief survey of the state of the art in this area, including brief introductions, summaries, or comments of the presentations in the same session. Each short presentation (10 minutes) should focus more on the method and result, and skip or just briefly mention the introduction/motivation. Following all the presentations in the same session will be a small panel by all the presenters in the session for a brainstorming discussion (about 30 minutes), including answering questions from the audience. A coordinator and a scribe will be appointed for each session to facilitate the discussion and record the major points, respectively. A summary of the discussion for each session will be published on the workshop website [2] after the workshop. We hope such an arrangement can make the workshop to have a more interactive atmosphere. 4. REFERENCES [1] http://answers.yahoo.com/. [2] http://www.buyans.com/qaweb2008/. 1275