Elsnet
 
   


ELSNET-list archive

Category:   E-CFP
Subject:   Robust Methods in Analysis of Natural Language Data
From:   Vincenzo Pallotta
Email:   Vincenzo.Pallotta_(on)_epfl.ch
Date received:   07 May 2001
Deadline:   30 Jun 2001

Call for Papers for a Special Issue of the Journal Natural Language Engineering on Robust Methods in Analysis of Natural Language Data Special Issue guest editors: Afzal Ballim Vincenzo Pallotta Department of Computer Science Swiss Federal Institute of Technology - Lausanne. The automated analysis of natural language data has become a central issue in the design of Intelligent Information Systems. The term "natural language" is intended to cover all the possible modalities of human communication and it is not restricted to written or spoken language. Processing unrestricted natural language is still considered as an AI-hard task. However various analysis techniques have been proposed in order to address specific aspects of natural language. In particular, recent interest has been on providing approximate analysis techniques, assuming that perfect analysis is not possible, but that partial results are still very useful. There are many ways in which the topic of robustness may be tackled: as a competency problem, as a problem of achieving interesting partial results, as a shallow analysis method, etc. What they have in common is that no simple combination of "complete" analysis modules for different linguistic levels in a chain can give a robust system, because they cannot adequately account for real-world data. Rather, robustness must be considered as a system-wide concern. We consider of central interest improving and integrating various processing methods with respect to the following issues: * Extending coverage * Improving efficiency * Disambiguation ability * Approximate processing * Enhancement of underlying theories Robustness may be seen as an engineering "add-on" - something that we add to a system to take account of the inability of our theories to cope with real-world data - or as a basic element of our theories - our theories are developed to admit that understanding of the domain can be incomplete. Both approaches may be valid under certain circumstances. The main goal of this Special Issue of the Natural Language Engineering journal is devoted to advances in fields like artificial intelligence, computational linguistics, human-computer interaction, cognitive sciences who are faced with the problem of feasible and reliable NLP systems implementation. Theoretical aspects of robustness in NLP are welcome as well as engineering and industrial experiences. We invite papers on all topics related to Robustness in Natural Language Processing and Understanding, including, but not limited to: Text Analysis Knowledge and Information Extraction Spoken Dialogue Systems Multimodal Human-Computer interfaces Natural Language Architectures Distributed NLP NLP and Soft Computing Semantics Underspecification Multimedia Document Analysis Robust Parsing Incremental Parsing Discourse analysis Summarization Complexity of linguistic analysis Hybrid methods in computational linguistics Text Mining Corpus linguistics Indexing and Information Retrieval SUBMISSION PROCEDURE: We are expecting full papers to describe original, previously unpublished research, be written in English, and not be simultaneously submitted for publication elsewhere (previous publication of partial results at workshops with informal proceedings is allowed). Papers should be formatted according to the NLE journal instructions and should be between 15 and 25 pages long. The preferred formatting system is LaTex, which can be used for direct typesetting, and a style file is available through anonymous ftp from the following address: ftp.cup.ca m.ac.uk/pub/texarchive/journals/latex/nle-sty/. In case of difficulty there is a helpline available on e-mail: texline_(on)_cup.cam.ac.uk. If LaTex is not available, the publisher may be able to use alternative formatting systems (please specify which was used (e.g. WordPerfect 5.0, MSWord2000,etc.)), but reserves the right in all cases to typeset any paper by conventional means. IMPORTANT DATES: Papers due: 30 June 2001 Acceptance notice: 30 October 2001 Final version due: 31 January 2002 Journal publication: (after March 2002) REVIEWING COMMITTEE: Jerry Hobs Massimo Poesio Karsten Worm Fabio Ciravegna John Carroll Ted Briscoe Michael Hess Kay-Uwe Carstensen Susan Armstrong Yorik Wilks Dan Cristea Liviu Ciortuz Eric Wherli Fabio Rinaldi Rodolfo Delmonte Wolfgang Menzel Salah Ait-Mokhtar Alberto Lavelli Rens Bod Joachim Niehren Roberto Basili Maria Teresa Pazienza Manuela Boros Diego Mollá-Aliod Hervé Bourlard B. Srinivas C.J. Rupp Peter Asveld Hatem Ghorbel Giovanni Coray Martin Rajman Jean-Cédric Chappelier ABOUT THE JOURNAL Natural Language Engineering is an international journal designed to meet the needs of professionals and researchers working in all areas of computerised language processing, whether from the perspective of theoretical or descriptive linguistics, lexicology, computer science or engineering. Its principal aim is to bridge the gap between traditional computational linguistics research and the implementation of practical applications with potential real-world use. As well as publishing research articles on a broad range of topicsfrom text analysis, machine translation and speech generation and synthesis to integrated systems and multi modal interfaces the journal also publishes book reviews. Its aim is to provide the essential link between industry and the academic community. Natural Language Engineering encourages papers reporting research with a clear potential for practical application. Theoretical papers that consider techniques in sufficient detail to provide for practical implementation are also welcomed, as are shorter reports of on-going research, conference reports, comparative discussions of NLE products, and policy-oriented papers examining e.g. funding programmes or market opportunities. All contributions are peer reviewed and the review process is specifically designed to be fast, contributing to the rapid publication of accepted papers. Editors B. K. Boguraev IBM Thomas J. Watson Research Center, New York, USA Christian Jaquemin University of Paris (LIMSI), FR John I. Tait University of Sunderland, UK FOR MORE INFORMATION: http://lithwww.epfl.ch/romand2 000/nle.html For any information related to the organization, please contact: Vincenzo Pallotta DI-LITH EPFL IN F Ecublens 1015 Lausanne Switzerland tel. +41-21-693 52 97 fax. +41-21-693 52 78 Vincenzo.Pallotta_(on)_epfl.ch
 

[print/pda] [no frame] [navigation table] [navigation frame]     Page generated 14-02-2008 by Steven Krauwer Disclaimer / Contact ELSNET