NLP -- Some Project Relevant References

AUTOMATIC ASSESSMENT

TRANSFORMATION-BASED LEARNING / POS TAGGING

MU-TBL is publicly available software for transformation based learning, by Torbjorn Lager. Papers/software available from his web pages at: http://www.ling.gu.se/~lager/mutbl.html

Some Brill papers at:

http://www.cs.jhu.edu/~brill/acadpubs.html

There's a brief overview of POS tagging, including a potentially useful list of references, at:

http://www.georgetown.edu/cball/ling361/tagging_overview.html

For handling of unknown words, could look at papers by Mikheev, available on:

http://www.cogsci.ed.ac.uk/~mikheev/papers.html

PROJECT GUTENBERG

Project Gutenberg makes books etc digitally available for free. Main site:

http://promo.net/pg/

UK mirror site:

ftp://ftp.mirror.ac.uk:21/sites/metalab.unc.edu/pub/docs/books/gutenberg

LATIN MORPHOLOGY

ftp://ftp.cogs.sussex.ac.uk/pub/nlp/DATR/papers/ceterisp.ps

ftp://ftp.cogs.sussex.ac.uk/pub/nlp/DATR/dtrfiles/latin_n.dtr

ROBUST PARSING/CHUNKING

http://lcg-www.uia.ac.be/conll2000/chunking/

http://www.sfs.nphil.uni-tuebingen.de/~abney/Papers.html

LANGUAGE IDENTIFICATION

http://www.i18ngurus.com/docs/998504805.html

MACHINE LEARNING PACKAGES

WEKA:

http://www.cs.waikato.ac.nz/~ml/weka/index.html

MU-TBL is publicly available software for transformation based learning, by Torbjorn Lager. Papers/software available from his web pages at: http://www.ling.gu.se/~lager/mutbl.html

DIALOGUE ARCHETECTURE

OAA - Open Agent Architecture - not stricty (or solely) for dialogue: http://www.ai.sri.com/~oaa/

GCSI - Galaxy Communicator Software Infrastructure: http://communicator.sourceforge.net/

Jaspis - a framework being used in a project at UMIST: http://www.cs.uta.fi/research/hci/spi/Jaspis/

QUESTION ANSWERING

The TREC publications are housed at: http://trec.nist.gov/pubs.html

Click for the year you're interested in (for QA, only 1999, 2000, or 2001). For each year, find the paper by Voorhees titled something like "Overview of the TREC-XX Question Answering Track". That will tell you who did best that year. You'll also find papers on the individual QA systems. For 1999 and 2000, the winning group was the one including S. Harabagiu and D. Moldovan.

A very simple QA system is described in R. J. Cooper and S. M. Rüger. A Simple Question Answering System. The Ninth Text REtrieval Conference (TREC 9),

READING COMPREHENSION

L. Hirschman, M. Light, E. Breck and J. Burger. Deep Read: A Reading Comprehension System. In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics, 1999

Riloff, and M. Thelen. A Rule-based Question Answering System for Reading Comprehension Tests. ANLP/NAACL-2000 Workshop on Reading Comprehension Tests as Evaluation for Computer-Based Language Understanding Systems

DIALOGUE ACT TAGGING/CLASSIFICATION

The following two papers are available from Ken Samuel's homepage at: http://www.eecis.udel.edu/~samuel/work/resume/resume.html#papers

Ken Samuel, Sandra Carberry and K. Vijay-Shanker. 1998. Dialogue Act Tagging with Transformation-Based Learning. in Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th Annual International Conference on Computational Linguistics, volume 2, pages 1150--1156, Montreal.

Ken Samuel, Sandra Carberry and K. Vijay-Shanker. 1999. Automatically Selecting Useful Phrases for Dialogue Act Tagging. In: Proceedings of the Fourth Conference of the Pacific Association for Computational Linguistics, Waterloo, Ontario, Canada.

Andreas Stolcke, Klaus Ries, Noah Coccaro, Elizabeth Shriberg, Rebecca Bates, Daniel Jurafsky, Paul Taylor, Rachel Martin, Carol Van Ess-Dykema and Marie Meteer. 2000. Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech. Computational Linguistics, 26(3): pages 339--373. Copy available at: ftp://ftp.dcs.shef.ac.uk/share/nlp/amities/bib/CompLing.pdf

GENERAL NLP RESOURCES PAGES