Data-Oriented Parsing (DOP) models of
natural language embody the assumption that human language perception and
production work with representations of past language experiences, rather than
with abstract grammatical rules. These models operate by decomposing the given
representations into fragments and recomposing those pieces to analyze new
utterances. DOP is therefore a new way to think of what a native speaker knows
when s/he knows a language. These papers describe ongoing efforts to develop a
data-oriented probabilistic approach to LFG-parsed corpora.
Recent Books
R. Bod, J. Hay and S. Jannedy (eds.), 2003. Probabilistic
Linguistics. The MIT Press.
R. Bod, R. Scha and K. Sima'an (eds.), 2003.
Data-Oriented
Parsing. CSLI Publications, University of Chicago Press.
Articles
Mary Hearne and Khalil Sima.an, 2003. Structured
Parameter Estimation for LFG-DOP by Backoff, Proceedings of
International Conference on Recent Advances in Natural Language Processing,
RANLP-03.
Andy Way, 2003. Machine Translation
with LFG-DOP. In R. Bod, R. Scha and K. Sima.an (eds.), Data-Oriented
Parsing, CSLI Publications.
Rens Bod and Ronald Kaplan, 2003. A Data-Oriented Parsing
Model for Lexical-Functional Grammar. In R. Bod, R. Scha and K. Sima.an
(eds.), Data-Oriented
Parsing, CSLI Publications.
Andy Way, 2003. Translating with
Examples: The LFG-DOT Models of Translation. In M. Carl and A. Way (eds.), Recent
Advances in Example-Based Machine Translation, Kluwer Academic Publishers.
Andy Way, 2001. Solving
Headswitching Translation Cases in LFG-DOT. Proceedings of the LFG'01
Conference. University of Hong Kong, China.
Andy Way, 2001. LFG-DOT: A Hybrid
Archtecture for Robust MT. PhD thesis, University of Essex, UK.
Rens Bod, 2000. An Improved Parser for
Data-Oriented Lexical-Functional Analysis. Proceedings ACL-2000,
Hong Kong, China.
Rens Bod, 2000. An Empirical Evaluation of
LFG-DOP. Proceedings COLING-2000, Saarbruecken, Germany.
Nicola Cancedda and Christer Samuelsson,
2000. Experiments with Corpus-based LFG-specialization. Proceedings
ANLP-2000, Seattle, Washington.
Boris Cormons, 1999. Analyse et
désambiguïsation: Une approche à base de corpus (Data-Oriented Parsing) pour
les représentations lexicales fonctionnelles. PhD thesis, Université de
Rennes, France.
Andy Way, 1999. A Hybrid Archtecture
for Robust MT using LFG-DOP. Journal of Experimental and Theoretical
Artificial Intelligence 11(4) (Special Issue on Memory-Based Language
Processing)
Rens Bod and Ronald Kaplan, 1998. A
Probabilistic Corpus-Driven Model for Lexical-Functional Analysis. Proceedings
of ACL/COLING '98, Montreal, Canada.
Rens Bod and Ronald Kaplan, 1998.
Grammaticality, Robustness, and Specificity in a Probabilistic Approach to
Lexical Functional Analysis. Proceedings LFG Conference and Workshops.
Brisbane, Australia.
Ronald Kaplan, 1996. A probabilistic
approach to LFG. http://www-lfg.stanford.edu/pubs/lfg-presentations/LFG96/kaplan-doptalk.ps.
Slides of the keynote lecture held at LFG-workshop, Grenoble
Background information on DOP
For more information on Data-Oriented
Parsing, see the home page of Rens
Bod .
LFG-parsed corpora
Home page of Anette Frank.
Other directions
For other probabilistic approaches to LFG,
see the home pages of Mark
Johnson and Stefan
Riezler.