Sebastian Varges

Sebastian Varges

Background Research Interests Projects Publications Bonus Question

Information Technology Research Institute (ITRI),
University of Brighton,
Lewes Road,
Brighton,
BN2 4GJ, UK.

Tel.: + 44 1273 642906
Fax: + 44 1273 642908
email: sebastian.varges + AT + itri.brighton.ac.uk

Background: I am a research fellow at the ITRI , University of Brighton, working on the TUNA project. Before moving to Brighton in October 2003, I did a PhD at the ICCS, University of Edinburgh, titled "Instance-based Natural Language Generation". I obtained an undergraduate degree in Computational Linguistics from Saarbrücken University and a Master's degree from the University of Düsseldorf.

Research Interests:

Natural language generation (NLG), dialogue systems and natural language processing in general: NLG may turn out to be the key for natural language understanding, especially in the context of dialogue systems, if we want to understand what the other has said - and why.
Combining rule-based and machine learning techniques such as instance-based learning: can we combine the strengths of both but avoid their disadvantages? I am particularly interested in working with small amounts of training data and rule systems of limited complexity.
Programming languages, environments and systems: we are still developing most research software from scratch - what languages and programming environments are most suitable for collaborative software development?

Current and past projects:

TUNA (ITRI, Brighton): In the TUNA project, we develop algorithms for referring expression generation (GRE). I am particularly interested in applying the "overgeneration and ranking" approach I previously used for surface realization in NLG to a higher-level content determination task such as GRE (Oct. 2003 - current):
BEETLE (University of Edinburgh): I developed an XSLT-based generator for the BEETLE tutorial dialogue system (Jan. - Sept. 2003 ).
M-Piro (University of Edinburgh): I worked on enhancing the expressive capabilities of M-Piro, the Java version of the ILEX generator, for a few months in 2002.
Computational Linguistics project at the University of Düsseldorf, headed by James Kilbury: between 1994 and 1998 I

developed a bottom-up parser for HPSG-style sign-based grammars, and
ported an implementation of the lexical knowledge representation language DATR to SICStus prolog for UNIX (there is a documentation page for the Düsseldorf-based implementation of DATR which I set up before I left in 1998.)

Publications:

2005, with Kees van Deemter. Generating referring expressions containing quantifiers. Proceedings of the 6th International Workshop on Computational Semantics (IWCS-6). Tilburg, 12-14 January 2005. [pdf]

2004. Overgenerating Referring Expressions Involving Relations. Proceedings of the Third International Conference on Natural Language Generation (INLG-04), pages 171-181. Brockenhurst, UK. Springer, 2004. [postscript, pdf]

2004. Johanna Moore, Kaska Porayska-Pomsta, Sebastian Varges, and Claus Zinn: Generating Tutorial Feedback with Affect. Proceedings of the Seventeenth International Florida Artificial Intelligence Research Symposium Conference (FLAIRS), AAAI Press, 2004. [pdf]

2003. Instance-based Natural Language Generation. Phd Thesis. Institute for Communicating and Collaborative Systems, School of Informatics, University of Edinburgh. [abstract, postscript, pdf]

2002. Fluency and Completeness in Instance-based Natural Language Generation. Proceedings of the 19th International Conference on Computational Linguistics (COLING), pages 1058-1064. Taipei, Taiwan. [postscript, pdf]

2001, with Chris Mellish. Instance-based Natural Language Generation. Proceedings of the 2nd Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL-01), pages 1-8. Carnegie Mellon University, Pittsburgh, PA, USA. [postscript, pdf]

1997: Master's thesis, University of Düsseldorf: "Parsing and generation in uniform architectures" (in German).

Bonus Question: What does the page design remind you of?