linguistlist.org>
Editor for this issue: Anita Huang <anitalinguistlist.org>
itl.atr.co.jp>Call for Papers The International Journal of Human-Computer Studies will publish a special issue on the theme Collaboration, Cooperation and Conflict in Dialogue Systems =========================================================== This special issue is devoted to theoretical and empirical studies of cooperation and collaboration in dialogue systems, addressing problems specific to dialogue management. It is associated with the workshop on the same theme held at IJCAI-97 in Nagoya but seeks submissions from all researchers who have been working on the topic, not just the workshop participants. Work on autonomous cooperative systems has shown the importance of collaboration in different domains: besides collaborating with users to provide requested information and to solve their problems, the systems should also be able to collaborate with other specialist intelligent systems (as in multi-agent infrastructures, for example). Also, research in natural language dialogue has brought new insights about collaboration: how mutual belief is established in dialogue (and, consequently, task) fulfillment, as well as how to cooperate to enable successful communication between the conversants. The notions of cooperation and collaboration are closely related to each other, but likely not the same: cooperation is one of the design principles for dialogue systems, but such systems do not necessarily collaborate with the user. To what degree is cooperation necessary for collaboration and how does it appear in dialogue? Cooperation turns into benevolence if the agent attempts to fulfill the partner's goals without questioning their contextual relevance, but this is not necessarily collaboration. On the other hand, if the agents pursue their own goals without considering those of their partners or the joint task, their actions can hardly be described as cooperative or collaborative. This special issue concentrates on human-human and human-computer communication, and on the ways cooperation and collaboration are manifested in these situations: how the partners jointly construct dialogue acts, infer non-explicitly expressed intentions, negotiate appropriate references, generate cooperative answers, co-produce utterances, give feedback, help each other in task achievement, etc. Since collaboration and cooperation are also related to conflict situations, arising from misunderstandings, erroneous perception, partial knowledge, false beliefs, etc., submissions that examine how cooperation and collaboration work in solving conflicts, and how the partners negotiate to reach a mutually acceptable resolution are also welcome. We encourage submissions on different aspects of cooperation and collaboration, addressing especially one or more of the following research issues: - How can we define "collaborative dialogues"? Are all dialogues collaborative? How do corpus studies back up the classification? - What kind of individual commitments are needed for collaboration? How do social settings (roles, acquaintance) affect communication and collaboration? How are these commitments and settings represented in a dialogue model? - What is the role of cooperation in collaborative dialogue? Can collaborative activity include benevolent or uncooperative behaviour? Does collaboration require sincerity (e.g., can cheating be collaborative)? - How does collaboration contribute to conflict resolution and recovery from misunderstandings? How can costs and benefits of collaboration be measured? - How is collaboration and cooperation related to task performance? What mechanisms are needed to combine collaborative task plans with dialogue contributions? - How can cooperation/collaboration principles and mechanisms be expressed in formal, computational models of communication or interaction? How can these models be implemented? - Is collaboration the main issue to problems in dialogue management? What are the solutions, future research problems? Both theoretical and more practically oriented papers are welcome, but we encourage papers that provide real-world examples of collaboration, cooperation and conflict, and compare multiple ways of addressing the problems that arise. SUBMISSION OF PAPERS Full paper submissions to the special issue should be in the IJHCS format. Information for the IJHCS authors can be found at: http://ksi.cpsc.ucalgary.ca/IJHCS/IJHCS_IA.html To help to coordinate the review process, authors who intend to submit are asked to send a short statement of intention to submit to David Sadek one month prior the deadline. The deadline for submissions is March 16. Submissions should preferably be sent as postscript files by email to: David.SadekMail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue
cs.vassar.edu>ACL/COLING-98 Workshop on TRANSLINGUAL INFORMATION MANAGEMENT CURRENT LEVELS AND FUTURE ABILITIES August 16, 1998 (following ACL/COLING-98) University of Montreal, Montreal (Quebec, Canada) CALL FOR PAPERS DESCRIPTION - --------- The development of natural language applications which handle multi-lingual and multi-modal information is the next major challenge facing the field of computational linguistics. Over the past 50 years, a variety of language-related capabilities has been developed in areas such as machine translation, information retrieval, and speech recognition, together with core capabilities such as information extraction, summarization, parsing, generation, multimedia planning and integration, statistics-based methods, ontologies, lexicon construction and lexical representations, and grammar. The next few years will require the extension of these technologies to encompass multi-lingual and multi-modal information. Extending current technologies will require integration of the various capabilities into multi-functional natural language systems. However, there is today no clear vision of how these technologies could or should be assembled into a coherent framework. What would be involved in connecting a speech recognition system to an information retrieval engine, and then using machine translation and summarization software to process the retrieved text? How can traditional parsing and generation be enhanced with statistical techniques? What would be the effect of carefully crafted lexicons on traditional information retrieval? This workshop is a follow-on to an NSF-sponsored workshop held in conjunction with the First International Conference on Language Resources and Evaluation in Granada, Spain (May 1998), at which an international panel of invited experts will consider these questions in an attempt to identify the most effective future directions of computational linguistics research--especially in the context of the need to handle multi-lingual and multi-modal information. The follow-on ACL workshop is intended to open the discussion to the computational inguistics community as a whole. The workshop will include ample time for discussion. A report summarizing the discussions at Granada will be available before the ACL workshop. TOPICS - ---- The workshop will focus on the following fundamental questions: 1. What is the current level of capability in each of the major areas of the field dealing with language and related media of human communication? 2. How can (some of) these functions be integrated in the near future, and what kind of systems will result? 3. What are the major considerations for extending these functions to handle multi-lingual and multi-modal information, particularly in integrated systems of the type envisioned in (2)? In particular, we will consider these questions in relation to the following areas: o multi-lingual resources (lexicons, ontologies, corpora, etc.) o information retrieval, especially cross-lingual and cross-modal o machine translation o automated (cross-lingual) summarization and information extraction o multimedia communication, in conjunction with text o evaluation and assessment techniques for each of these areas o methods and techniques (both statistics-based and linguistics- based) of pre-parsing, parsing, generation, information acquisition, etc. We invite submissions which report on work in these areas. All papers should clearly identify how the work addresses the issues and questions outlined above. SUBMISSIONS - --------- Only hard-copy submissions will be accepted. Authors should submit six (6) copies of the full-length paper (3500-5000 words). Submissions should be sent to: Nancy Ide Department of Computer Science Vassar College 124 Raymond Avenue Poughkeepsie, New York 12604-0520 USA Style files and templates for preparing submissions can be found at http://coling-acl98.iro.umontreal.ca/Styles.html The official language of the conference is English. IMPORTANT DEADLINES - ----------------- Submission Deadline: March 23, 1998 Notification Date: May 15, 1998 Camera ready copy due: June 15, 1998 SCIENTIFIC COMMITTEE - ------------------ Charles Fillmore University of California Berkeley, USA Robert Frederking Carnegie Mellon University, USA Ulrich Heid (tentative) University of Stuttgart, Germany Eduard Hovy Information Sciences Institute, USA Nancy Ide Vassar College, USA Lauri Karttunen (tentative) Rank Xerox Research, France Kimmo Koskenniemi (tentative) University of Helsinki, Finland Mun Kew Leong National University of Singapore Joseph Mariani LIMSI/CNRS, France Mark Maybury The Mitre Corporation, USA Sergei Nirenburg (tentative) New Mexico State University, USA Akitoshi Okumura (tentative) NEC, Japan Martha Palmer University of Pennsylvania, USA James Pustejovsky Brandeis University, USA Peter Schaueble ETH, Switzerland Oliviero Stock IRST, Italy Felisa Verdejo UNED, Spain Piek Vossen University of Amsterdam, Netherlands Wolfgang Wahlster DFKI, Germany ORGANIZERS - -------- Robert Frederking, Carnegie Mellon University, USA Eduard Hovy, ISI, University of Southern California, USA Nancy Ide, Vassar College, USA INFORMATION - --------- Information on the workshop can be found at http://www.cs.vassar.edu/~ide/translingual.html Inquiries may be addressed to the organizers: Robert Frederking <refMail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue