linguistlist.org>
Editor for this issue: Jody Huellmantel <jodylinguistlist.org>
cs.rutgers.edu>Call for papers Workshop on Data-driven MT ACL'2001 Conference Toulouse, France Invited speaker: Hermann Ney, RWTH Aachen Deadline for paper submissions: April 6, 2001 Deadline for notification of paper acceptance: April 27, 2001 Deadline for camera-ready papers: May 16, 2001 Workshop Date: July 7, 2001 Details on submissions listed below. With the increased availability of online corpora, data-driven approaches have become central to the NL community. A variety of data-driven approaches have been used to help build Machine Translation systems -- example-based, statistical MT, and other machine learning approaches - and there are all sorts of possibilities for hybrid systems. We wish to bring together proponents of as many techniques as possible to engage in a discussion of which combinations will yield maximal success in translation. We propose to center the workshop on Data Driven MT, by which we mean all approaches which develop algorithms and programs to exploit data in the development of MT, primarily the use of large bilingual corpora created by human translators, and serving as a source of training data for MT systems. We are specifically interested in papers about * statistical machine translation (modeling, training, search) * machine-learning in translation * example-based machine translation * acquisition of multilingual training data * evaluation of data driven methods (also with rule-based methods) * combination of various translation systems; integration of classical rule-based and data driven approaches * word/sentence alignment methods An especially important question that we wish to address is which techniques are best for each of the subparts of a complete MT system - e.g. learning grammars, building lexicons, parsing input data, determining transfer principles, generating target text, etc. We will strongly encourage papers on systems which show demonstrable progress over previously chosen methods, and which have been integrated in an actual end-to-end system. Test results or demos will be given strongest preference for participation. Organizers: Jessie Pinkham, Microsoft Research jessiepMail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue
uwe.ac.uk>DEADLINE EXTENDED TO MARCH 12!!! Call for Participation: Evolutionary COmputation and Multi-Agent Systems (ECOMAS) http://www.csm.uwe.ac.uk/~rsmith/ECOMAS A Birds-Of-A-Feather Workshop At GECCO 2001 http://gal4.ge.uiuc.edu:8080/gecco-2001/ Extended: Submissions Due: March 12, 2001 Workshop Date: July 7, 2001 Description Of The Workshop Topic Multi-agent systems (MAS) are collections of interacting autonomous entities. The behaviour of the MAS is a result of the repeated asynchronous action and interaction of the agents. Understanding how to engineer adaptation and self-organisation is thus central to the application of agents on a large scale. Moreover, multi-agent simulations can also be used to study emergent behaviour in real systems. Desirable self-organisation is observed in many biological, social and physical systems. However, fostering these conditions in artificial systems proves to be difficult and offers the potential for undesirable behaviours to emerge. Thus, it is vital to be able to understand and shape emergent behaviours in agent based systems. Current mathematical and empirical tools give only a partial insight into emergent behaviour in large, agent-based societies. EC provides on paradigm for addressing this need. Moreover, EC techniques are inherently based on a distributed paradigm (natural evolution), making them particularly well suited for adaptation in agents. At the same time, ideas from natural ecosystems or economies, such as resource flows, niches, and spatial context or neighbourhood can contribute both to the development of MAS and to the improvement of EC techniques. The interaction between these different sources of natural inspiration and the two computing disciplines of MAS and EC is beginning to stimulate a range of systems with properties that extend the MAS and EC concepts in new and interesting directions. Notable examples of systems of that begin to examine the issues of EC in MAS include Holland's ECHO system, Tierra, Avalanche, Egglets, Amalthaea, InfoSpiders, and many others . The goal of EcoMAS is to open a dialog among researchers and practitioners who are examining EC in MAS. EcoMAS represents an important opportunity for those active or interested in this area to hear about current work, discuss future directions and priorities, and form invaluable research contacts. Interest To The GEC Community With the advance of computational power and communications speed, we now live in a computational world where a large number of agents may be working on behalf of any given user. A large number of Internet software agents may be acting on behalf of even the most casual user: searching for music, comparing pension schemes, purchasing good and services, identifying chat partners, etc. Moreover, these agents may be collaborating with those of other users, while spawning and managing agents of their own. In more formal settings, a business, academic, or government user may simultaneously employ many software agents to manage workflow, trade goods or information, collaboratively solve problems, etc. In the future, even relatively simple household appliances may play a role in this churning system of interacting, computational agents. In this world, EC theories and practices have new implications. Agents that interact according to these theories are no longer locked inside the laboratory conditions imposed by EC researchers and users.The interest in merging the EC and MAS research communities is certainly growing. In the opinion of the organizers, it is important to the GEC community that there is a forum to discuss the particular issues of EC in MAS. Simultaneously, such a forum allows for ideas from contemporary MAS research to spread to the GEC community. Workshop Format In the opinion of the organizers, it is important that a workshop involve more than talks and presentations. Therefore, the workshop will be focused on an extensive, directed discussion on the future of EC in MAS. Other aspects of the workshop will be directed at facilitating this discussion: 1) The workshop will allow for the selected presenters to post "mini-posters." Much of this material will be available before the workshop, via a web site. 2) 3) The first hour of the workshop will consist of "mini-presentations" to preview the mini-poster session. Authors will be allowed to present at most two transparencies. Time constraints will be adjusted, depending on the number of presenters selected, but a limit will be maintained, to allow for the sessions outlined below. 4) 5) The second hour of the workshop will consist of a mini-poster session. 6) 7) The third hour of the workshop will focus on a discussion of the future of EC in MAS. 8) 9) The final, and perhaps most important, hour of the workshop will be a discussion focused on action items for advancing EC in MAS. The organizers feel that explicitly providing time to discuss agendas in the fashion will give the workshop an atypical, meaningful outcome. 10) Submission Instructions If you would like to present material at the workshop (in the format noted above), please submit a 4 page extended abstract in Postscript or PDF form to cefn.hoileMail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue