linguistlist.org>
Editor for this issue: Ann Dizdar <annlinguistlist.org>
cs.columbia.edu>ACL'97/EACL'97 Workshop on INTELLIGENT SCALABLE TEXT SUMMARIZATION (at ACL'97/EACL'97 Joint Conference) Madrid, Spain July 11 or 12, 1997 CALL FOR PAPERS (http://www.cs.columbia.edu/~radev/ists97) With the explosion in the quantity of on-line information in recent years, demand for text summarization technology appears to be growing. Commercial companies are increasingly starting to offer text summarization capabilities, often bundled with information retrieval tools. These recent developments offer opportunities as well as substantial challenges for research in text summarization. In general, such developments create a practical need for summarization systems which scale up when applied to large volumes of unrestricted text. At ACL'97/EACL'97, a particular challenge is to identify the niches where natural language processing (NLP) can make an impact. For example, there are applications which require characterizing the content of large text collections to support data mining functions, but NLP has not been used much in such applications. Traditionally, shallower techniques have been leveraged to achieve the desired levels of scalability and domain-independence, but recent advances in robust information extraction as well as approaches integrating statistical and symbolic techniques open up possibilities for more powerful yet scalable summarization techniques. With the renewed interest in text summarization, another challenge is to develop criteria to help evaluate different methodologies, in order to better advise investors and the interested public on technology choices. While there have been focused workshops in the past on text summarization, they have pre-dated the tremendous expansion of on-line information access fueled by the recent growth of the World Wide Web. This workshop would bring together researchers interested in advancing the scientific frontiers of text summarization to meet these new practical challenges and opportunities. Submissions are invited on original research in all aspects of text summarization, including, but not limited to: * Statistical, linguistic, and knowledge-based techniques in intelligent summarization * Multimodal summarization strategies * Exploiting advances in information extraction in summarization * Text generation for scalable summarization * Classification criteria for summarization systems * Evaluation methods and metrics * Summarization in operational contexts: requirements, architectures, lessons learned * Tailoring summaries to particular users, tasks, and contexts * Theoretical foundations, including cognitive models * Combining scalability with abstraction in summarization * Summarization across multiple documents/sources * Multilingual summarization Criteria for selection will include clarity, originality, relevance, and significance of results. Attendees at the workshop MUST register for the main ACL/EACL conference. PROGRAM COMMITTEE Udo Hahn University of Freiburg Julian Kupiec Xerox Palo Alto Research Center Inderjeet Mani The MITRE Corporation (co-chair) Mark Maybury The MITRE Corporation (co-chair) Kathy McKeown Columbia University Boyan Onyshkevych US Department of Defense Dragomir Radev Columbia University Lisa Rau SRA International Kazuo Tanaka NTT Human Interface Laboratories SUBMISSION INFORMATION DEADLINE FOR SUBMISSION: March 15, 1997 Acceptance Notification: April 28, 1997 Interested participants should submit a previously unpublished paper addressing a specific text summarization issue or reporting novel methods and results. Authors should indicate whether the paper is being submitted elsewhere. As the papers will be reviewed anonymously, please do not include author names in the body of the paper; instead provide a separate title page with title, author names and email addresses. The paper length (excluding separate title page) should be no longer than 8 pages. For email submissions, please submit postscript. (If the postscript doesn't print properly here, you may eventually have to submit a hardcopy, so please budget enough time for that.) For hardcopy submissions, please submit FIVE copies of the paper. Please send submissions to: Inderjeet Mani The MITRE Corporation, W640 1820 Dolley Madison Blvd McLean, VA 22102-3481, USA Phone: 1-703-883-6149 Fax: 1-703-883-1279 Email: imaniMail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue
mail4.ai.univie.ac.at>FIRST CALL FOR PAPERS AND PARTICIPATION for the Workshop on "CONCEPT to SPEECH GENERATION SYSTEMS" Friday, July 11, 1997 in conjunction with 35th Annual Meeting of the Association for Computational Linguistics (ACL'97/EACL'97 Joint Conference) July 7-11, 1997 Madrid, Spain Information about the workshop can also be retrieved from: http://www.dfki.uni-sb.de/~finkler/acl97-cts/index.html - ------------------- FOCUS OF THE WORKSHOP - ------------------- Concept-to-Speech (CTS) generation, i.e., the production of synthetic speech on the basis of pragmatic, semantic, and discourse knowledge offers a challenging and relatively new field of research in intelligent user interfaces. The questions raised in such an environment range from pragmatics, semantics, and (morpho-)syntax to phonology and phonetics. The modelling of prosody (at symbolic and acoustic level) serves as one of the open questions within this paradigm. Obviously, the development of a CTS system is very demanding. Successful work within the framework of CTS relies on the ability to integrate efforts from a number of disciplines, such as Computational Linguistics, Artificial Intelligence, Cognitive Science, and Signal Processing. The workshop will provide a forum to bring together researchers from the fields of natural language generation and speech synthesis. The aim of the workshop is to stimulate interchange of innovative ideas and results of diverse aspects of CTS generation in order to bridge the gap between these fields. Among the challenging aspects of a CTS system, we propose to address issues of the following list in the first place: * How can systems for natural language generation be adapted in order to utilize new realization options to the generation process that are offered in the CTS framework? * How can issues in the time-course of the interleaved process for generation and synthesis (when-to-say) be dealt with? Which requirements on speech synthesis are to be fulfilled in an incremental approach to spoken language production? * Due to its inherent integrational property, being influenced by a whole number of representational levels, modelling of prosody will be one of the major topics of the workshop. * How can approaches in the Text-to-Speech tradition to synthesis show their adaptability to Concept-to-Speech? We invite contributions that provide solutions to any of the topics indicated above or that present innovative applications addressing the abovementioned issues. - ---------------- PROGRAM COMMITTEE - ---------------- Robert BANNERT Univ. of Umea, Sweden John BATEMAN, GMD Darmstadt, Germany Mary BECKMAN, Ohio State Univ., USA Carlos GUSSENHOVEN, Univ. of Nijmegen, The Neatherlands Bjorn GRANSTROeM, KTH Stockholm, Sweden Elisabeth MAIER, DFKI Saarbruecken, Germany Scott PREVOST, MIT Boston, USA Mark STEEDMAN, Univ. of Pennsylvania, USA - ------------- WORKSHOP FORMAT - ------------- The workshop will be a full-day event that provides a forum for individual presentations as well as group discussions. In the presentation part, authors of accepted papers will describe their results and positions (about 30 minutes each). A plenary discussion of about one hour length will take place. - ------------------------ REQUIREMENTS & SUBMISSIONS - ------------------------ Authors should submit a full length paper not exceeding 3200 words (exclusive of references). Due to tight time constraints, initial submissions and reviewing will be handled exclusively electronically. Joint submissions with the `Interactive Spoken Dialog Systems' ACL/EACL workshop are allowed. If there are sufficient joint submissions a joint session may be scheduled. Please indicate on the title page that your abstract is a joint submission. Submissions must use the ACL submission style (aclsub.sty) retrievable from the ACL LISTSERV server via anonymous ftp: ftp ftp.cs.columbia.edu Name: anonymous Password: <your email address> cd acl-l/ACL97 get aclsub.sty Submissions have to be mailed as a single LaTeX file or a single postscript file. Mails should be sent to cts-97Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue