linguistlist.org>
Editor for this issue: Karolina Owczarzak <karolinalinguistlist.org>
cs.rutgers.edu>Call for Papers HLT-NAACL03 Workshop on Learning Word Meaning from Non-Linguistic Data 31 May 2003 Edmonton, Canada Home page: http://www.cs.cornell.edu/~regina/lwm03/ HLT-NAACL03 Home page: http://www.sims.berkeley.edu/research/conferences/hlt-naacl03 Endorsed by: SIGSEM, the ACL Special Interest Group in Computational Semantics SIGGEN, the ACL Special Interest Group in Generation SIGLEX, the ACL Special Interest Group on the Lexicon One of the grand challenges of NLP, AI, and Cognitive Science is to develop models of what words mean (lexical semantics) in terms of the non-linguistic world. Recently there has been growing interest in using corpus and data based techniques for this task. In other words, trying to learn what words mean by analysing a 'parallel corpus' of (A) non-linguistic data and (B) linguistic texts that describe or otherwise are based on the non-linguistic data. Recent examples of such work include learning verb semantics from visual-image sequences; learning the meaning of time phrases from a collection of weather forecasts based on numerical weather simulations; and learning the meaning of mathematical predicates from human verbalisations of theorem-prover output. We invite people interested in this topic to submit papers to the workshop. Possible topics include (but are not limited to) * Example analyses of word meanings based on non-linguistic data. * Discussion of relevant algorithms and techniques, for example for aligning texts with non-linguistic data. * Applications that exploit lexical semantic models learned from non-linguistic data. * Resources, such as parallel text-data corpora, that can be used by other researchers interested in this area. As this is a workshop, we welcome papers that present work in progress as well as papers that present completed work. Papers that focus on learning semantic information from conventional text-only corpora are less appropriate for this workshop, and should be submitted elsewhere. We hope that this workshop will help "gel" this new and exciting research area, by bringing together interested people who may not be aware of what is being done elsewhere. Participants from other area of AI and Cognitive Science are very welcome, including vision and robotics researchers who are interested in learning how to relate sensor data to words, and psychologists who are interested in cognitive models of how people learn to relate words to the non-linguistic world. SUBMISSIONS Papers should be between 4 and 8 pages long and in PDF format. Papers should be formatted according to the HLT-NAACL guidelines http://www.sims.berkeley.edu/research/conferences/hlt-naacl03/format.html Do not anonymise submissions, since reviewing for the workshop will not be blind. Authors are strongly encouraged to use the style files accessible through the above web page. Send your submission to Ehud Reiter (ereiterMail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue
cs.rutgers.edu>Workshop on The Software Engineering and Architecture of Language Technology Systems (SEALTS) HLT-NAACL03 31 May 2003 Edmonton, Canada http://www.it.usyd.edu.au/research/sealts.html Overview A number of researchers argued in the early and middle 1990s that the field of computational infrastructure, or architecture, for Natural Language Processing, merited an increase in attention. The reasoning was that the increasingly large-scale and technologically significant nature of NLP science was placing increasing burdens of an engineering nature on R&D workers seeking robust and practical methods. Over the intervening period a number of significant systems and practices have been developed in what we may call Software Architecture for Language Engineering. Of the most prominent are: RAGS, Reference Architecture for Generation Systems (Brighton and Edinburgh) LT XML (Edinburgh) TEI, CES, XCES (Oxford, Vassar, etc.) ATLAS (LDC, NIST) Galaxy Communicator Software Infrastructure (MIT & MITRE) ProtE9gE9 (Stanford) GATE, a General Architecture for Text Engineering (Sheffield) This workshop represents an opportunity for practitioners in this area to report their work in a coordinated setting. The value to the community at large will be to get a snapshot of the state-of-the-art in infrastructural work, which may indicate where further take-up of these systems can be of benefit Topics We solicit papers from the following research areas, and other allied topics: The Architecture of Language Technology Systems (LTS) Standards of best practice Standards for knowledge transfer and code sharing between LTS Language resource construction and management Relationship of LTS to Semantic Web architectures Engineering LTS for different purposes Comparative Reviews of Architectures Comparative experiments of different architectures and implementations Data Sharing in LT Systems Knowledge storage Message Passing LT System project management Strategies for Distribution and Scalability Data Models Instructions for Authors Due to the short time for submission two types of papers will be accepted, namely: Full papers: 7-8 pages Short papers: 1-6 pages. Short papers will be given half the speaking time of full papers. No differentiation will be made in the publication of the Proceedings. The Organisers reserve the right to request a paper to be reduced to short paper length if they believe it is appropriate. This policy is aimed at encouraging researchers who have experimental plans that have not yet been tested by implementation, or by papers that are exploratory or speculative. Significant review papers aimed to point the way to the future are also encouraged. Submissions Papers should be in PDF format and formatted according to the HLT-NAACL guidelines (http://www.sims.berkeley.edu/research/conferences/hlt-naacl03/ format.html). Do not anonymize submissions, since reviewing for the workshop will not be blind. Authors are strongly encouraged to use the style files accessible through the above web page. Send your submission to Jon Patrick (jonpatMail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue