[Corpora-List] Call for Participation: Corpus Profiling Workshop at IIiX 2008

Kruschwitz U udo at essex.ac.uk
Tue Oct 7 16:39:16 CEST 2008

----------------------------------- CALL FOR PARTICIPATION -----------------------------------

Corpus Profiling for Information Retrieval and Natural Language Processing Workshop 2008 18 October 2008 London http://kmi.open.ac.uk/events/corpus-profiling/index.php

***Please note that there is no on-site registration***

----------------------------------- PURPOSE -----------------------------------

We aim to bring together people from different research communities interested in exploring how corpus characteristics affect the behaviour of techniques in information retrieval and natural language processing, and to set out a roadmap for a shared research agenda.

It is well known in NLP and IR that the effectiveness of a technique depends on both the data on which it is deployed and its match with the task at hand. In 1973, Spärck-Jones attributed differing degrees of success at automatic classification to differences in dataset characteristics. Since Croft and Harper (1979), IR performance has repeatedly been related to collection size and other features, though no upper bound has been found.

The importance of data and task dependencies has been highlighted in IR, anaphora resolution, automatic summarization and recently, in word sense disambiguation. Many web/enterprise web retrieval systems rely on URL properties, link graph properties, click streams, and so on, with performance dependent on the degree to which this evidence is present and meaningful in a particular corpus.

Systematically exploring features that can be used effectively to characterise corpora, has been missing from IR/NLP research. This creates problems with replicability of experimental results and the development of applications.

The time is right to pursue this dependence systematically to address topics in tracking the effect of dataset profile on technique performance. Over the past 15 years, the approaches of several subject areas have converged with IR, as large corpora and test collections assume central importance in research methodologies. These areas have highlighted issues surrounding the role of data.

----------------------------------- INVITED SPEAKERS -----------------------------------

Anne De Roeck (The Open University) Ruslan Mitkov (University of Wolverhampton) Michael Oakes (University of Sunderland) Leif Azzopardi, (University of Glasgow) Nikolaos Nanas (TBC), Centre for Research and Technology - Thessaly (CERETETH)

----------------------------------- ACCEPTED PAPERS -----------------------------------

Automatic Natural Language Style Classification and Transformation Foaad Khosmood and Robert A. Levinson (University of California, Santa Cruz)

Genre Analysis of Structured E-mails for Corpus Profiling Malcolm Clark (The Robert Gordon University), Ian Ruthven (University Strathclyde), Patrik O'Brian Holt (The Robert Gordon University)

Lexical Profiling of Existing Web Directories to Support Fine-grained Topic-Focused Web Crawling Mark Greenwood, Goran Nenadic (University of Manchester)

Building a document genre corpus: a profile of the KRYS I corpus Vera F. Berninger, Yunhyong Kim and Seamus Ross (University of Glasgow)

Distributional Lexical Semantics for Stop Lists Neil Cooke, Lee Gillam (University of Surrey)

----------------------------------- YOUR CONTRIBUTION -----------------------------------

We are looking forward to a very productive workshop with as much interaction as possible. As stated in the workshop aims we are to set out a roadmap for a shared research agenda. To do this most effectively we are asking participants to provide some input stating their views on corpus profiling for NLP and IR. Ideally this would be a short paragraph, suggestions for discussion or even a simple statement that should be submitted to the workshop organizers before the workshop. Any input is most welcome!

----------------------------------- REGISTRATION -----------------------------------

The registration fee will be £80. Registration is through the IIiX registration site: http://irsg.bcs.org/iiix2008/registration.php

More information about the Corpora mailing list