linguistlist.org>
Editor for this issue: Jody Huellmantel <jodylinguistlist.org>
cs.rutgers.edu>_______________________________________________________________ Preliminary Call for Papers NAACL 2001 Workshop on Adaptation in Dialogue Systems co-chairs: Cindi Thompson and Eric Horvitz The purpose of this workshop is to bring together researchers investigating the application of learning and adaptation to dialogue systems, both speech and text based. In this workshop we encourage papers on either theoretical or applied research in adaptation for dialogue, that includes learning procedures as well as decision making methods aimed at dynamically reconfiguring dialogue behavior based on the context. We would also like to explore techniques that allow a dialogue system to learn with experience or from data sets gathered from empirical studies. We welcome submissions from researchers supplementing the traditional development of dialogue systems with techniques from machine learning, statistical NLP, and decision theory. We solicit papers from a number of research areas, including: -Use of machine learning techniques at all levels of dialogue, from speech recognition to generation; from dialogue strategy to user modeling -Adapting to the user as a dialogue progresses -Dialogue as decision making under uncertainty -User and user group modeling -Use of corpora in developing components of dialogue systems, including issues in annotation -Evaluation of adaptive dialogue systems -Comparison of different techniques in applying adaptive techniques to dialogue We also hope to include a session for the demonstration of working systems, as time permits. The demonstration sessions will be open to anyone who wishes to bring their adaptive conversational systems for demonstration to other members of the workshop. Presenters are asked to submit a paper that is specifically directed at a demonstration of their current systems. A web site that will provide additional information on the workshop as it becomes available is located at: http://www.cs.utah.edu/~cindi/AdaptDial.html For more information: Please direct questions to Eric Horvitz (horvitzMail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue
cs.rutgers.edu>We are pleased to announce the following ACL sponsored workshop. NAACL 2001 Workshop Carnegie Mellon University, Pittsburg 3 or 4 June 2001 ------------------------------ - Adapting Lexical Resources - ------------------------------ http://www.dcs.shef.ac.uk/~marks/wshop Lexical resources have become important basic tools within NLP and related fields. The range of resources available to the researcher is diverse and vast - from simple word lists to complex MRDs and thesauruses. The resources contain a whole range of different types of linguistic information presented in different formats and at varying levels of granularity. Also, much information is left implicit in the description, e.g. the definition of lexical entries. The majority of resources used by NLP researchers were not intended for computational uses. For instance, WordNet was an experiment in modelling the mental lexicon and MRDs are a by-product of the dictionary publishing industry. The reasons for using these resources are simple: they are available (and in the case of WordNet, free). The cost of lexicon building is high and few research sites have the resources or inclination to carry out what Johnston called the "mindless drudgery" of manual lexicography. The alternative is to adapt existing resources to particular computational tasks. This workshop is concerned with automatic methods for carrying out this process. We are particularly interested in papers related to the following topics: - adapting resources to by making them reflect the lexical coverage within a particular domain - adapting resources for particular applications (e.g. information extraction, machine translation, question answering, information retrieval) - augmenting the information in a resource (e.g. adding extra word senses, enriching the information associated with the existing entries) - improving the consistency or quality of resources by e.g. merging resources, homogenizing lexical descriptions, making implicit lexical knowledge explicit and clustering word senses - combining the information in more than one resource e.g. by producing a mapping between their senses The overall aim of this workshop is to build up a picture of the current state-of-the-art techniques for automatically modifying lexicons. This picture will allow the NLP community to make more effective and efficient use of the lexical resources currently available. Important Dates - ------------- 26 January 2001 Deadline for submission of papers 16 February Notification of acceptance 1 March Camera-ready copies due 3 or 4 June Workshop Submissions - --------- We invite contributions of original research related to any of the topics of the workshop. Paper submissions should be no longer than 3000 words (including references) and should use the appropriate ACL latex style or Microsoft Word style. You can download the appropriate style or template files using the following links: Latex style sheet file http://www.isi.edu/natural-language/naacl01/naacl2001sub.sty bibliography file http://www.isi.edu/natural-language/naacl01/acl.bst sample latex file http://www.isi.edu/natural-language/naacl01/samplesub.tex sample bibliography file http://www.isi.edu/natural-language/naacl01/samplesub.bib Microsoft Word Template file http://www.isi.edu/natural-language/naacl01/naacl-2001-sub.dot Preferred submission format is as an electronic file sent to wimMail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue