Automatic summarization and question answering (QA) aim at producing a concise, condensed representation of the key information content in an information source for a particular user and task. Interest in automatic summarization and question answering continues to grow, motivated by the explosion of on-line information sources and advances in natural language processing and information retrieval. In fact, various forms of automatic summarization and question answering will undoubtedly be indispensable given the massive information universes that lie ahead in the 21st century.
Summarization and question answering involves the extraction or generation of text snippets to fulfill some user needs. Rule-based or statistical-based approaches to summarization and question answering systems have shown promising results in the TREC QA-tracks, NTCIR QAC, and NIST DUC; it is, however, very difficult to find good evaluation functions or rules that work well across domains or in all questions because there are many system parameters that must be carefully tuned in order to achieve good system performance. In consequence, various machine learning (ML) techniques have recently been applied to summarization and QA systems.
The purpose of this workshop is to provide a forum for exploring the commonality underling this diversity of problem domains and approaches.
The workshop has the following goals:
|
- |
to bring together communities of researchers who apply machine learning techniques to summarization and QA systems, |
|
- |
to deepen the summarization and QA community's understanding of the state of the art in machine learning, |
|
- |
to identify summarization and QA-related problems for which ML techniques might be appropriate, and |
|
- |
to advance the state of the art of summarization and QA technologies. |
Topics appropriate to this workshop include:
|
-
|
summarization or QA systems with ML techniques, |
|
-
|
novel or improved ML techniques for summarization or QA, |
|
-
|
effective feature extraction methods for characterizing summarization or QA, |
|
-
|
metrics and benchmarks for evaluating the effect of machine learning techniques in summarization or QA systems, |
|
-
|
generation for summarization or QA, |
|
-
|
cross-language or multilingual QA, |
|
-
|
integration with Web and IR access, |
|
-
|
corpora creation for summarization or QA, |
|
-
|
interfaces and tools for summarization or QA. |
Submissions are limited to original, unpublished work. Submissions must use the ACL latex style or Microsoft Word style MSQA-submission.dot (both available from the workshop web page). Paper submissions should consist of a full paper (5000 words or less, exclusive of title page and references). Papers outside the specified length are subject to be rejected without review. The paper should be written in English.
Please send submission questions to Abe Ittycheriah [abei@us.ibm.com].
Electronic submission only: send the pdf (preferred), postscript, or MS Word form of your submission to: Abe Ittycheriah [abei@us.ibm.com]. The Subject line should be "ACL2003 WORKSHOP PAPER SUBMISSION". Because reviewing is blind, no author information is included as part of the paper. An identification page must be sent in a separate email with the subject line: "ACL2003 WORKSHOP ID PAGE" and must include title, all authors, theme area, keywords, word count, and an abstract of no more than 5 lines. Late submissions will not be accepted. Notification of receipt will be e-mailed to the first author shortly after receipt.
| Paper submission deadline: | Apr 21, 2003 |
| Notification of acceptance for papers: | May 19, 2003 |
| Camera ready papers due: | May 26, 2003 |
| Workshop date: | July 11, 2003 |
| Abraham Ittycheriah | IBM T.J. Watson Research Center, USA |
| Tsuneaki Kato | University of Tokyo, Japan |
| Chin-Yew Lin | USC/ISI, USA |
| Yutaka Sasaki | NTT Communication Science Laboratories, Japan |
| Regina Barzilay | Cornell University, USA |
| Jason Chang | National Tsin-Hua University, Taiwan |
| Hsin-Hsi Chen | National Taiwan University, Taiwan |
| Jennifer Chu-Carroll | IBM T.J. Watson Research Center, USA |
| Udo Hahn | University of Freiburg, Germany |
| Sanda Harabagiu | Univ. of Texas, Dallas, USA |
| Donna Harman | NIST, USA |
| Ulf Hermjakob | USC/ISI, USA |
| Jerry Hobbs | USC/ISI, USA |
| Junichi Fukumoto | Ritsumeikan University, Japan |
| Gary Geunbae Lee | Postech, South Korea |
| Hideki Isozaki | NTT Communication Science Laboratories, Japan |
| Sadao Kurohashi | University of Tokyo, Japan |
| Hang Li | Microsoft Research Asia, China |
| Dekang Lin | University of Alberta, Canada |
| Bernardo Magnini | Istituto Trentino di Cultura (ITC)/IRST, Italy |
| Inderjeet Mani | MITRE Corp. USA |
| Shigeru Masuyama | Toyohashi University of Technology, Japan |
| Dan Moldovan | Univ. of Texas, Dallas, USA |
| Raymond J. Mooney | University of Texas at Austin, USA |
| Tatsunori Mori | Yokohama National University, Japan |
| Hwee Tou Ng | National University of Singapore, Singapore |
| Manabu Okumura | Tokyo Institute of Technology, Japan |
| John Prager | IBM Research, USA |
| Drago Radev | University of Michigan, USA |
| Dan Roth | University of Illinois at Urbana/Champaign, USA |
| Satoshi Sekine | New York University, USA |
| Karen Sparck-Jones | Cambridge University, UK |
| Tomek Strzalkowski | State University of New York, Albany, USA |
| Ingrid Zukerman | Monash University, Australia |