Grammatical Trigrams
A New Approach to Statistical Language Modeling
The Grammatical Trigrams project is carrying out research on
new algorithms for probabilistic models of natural language using
grammatical constraints and long-distance dependencies. The project
is developing new parsing technology and statistical modeling techniques with
the goal of improving applications such as automatic speech recognition and machine
translation. Press here for
further details on the objectives and methods of the project.
Principal Investigators
Graduate Students
This page
describes the underlying parsing technology that the project is developing. It includes
background information and an on-line demonstration of the system.
Publications
- D. Beeferman, A. Berger and J. Lafferty,
Text segmentation using exponential models,
[Abstract],
Proceedings of
the Second Conference On Empirical Methods in NLP,
Providence, RI, 1997.
- D. Beeferman, A. Berger, and J. Lafferty,
A Model of Lexical Attraction and Repulsion,
[Abstract],
Proceedings of the ACL-EACL'97 Joint Conference,
Madrid Spain, 1997.
- P. Placeway and J. Lafferty
Cheating with Imperfect Transcripts,
[Abstract],
Proceedings of ICSLP'96,
Philadelphia, PA 1996.
- J. Lafferty, Gibbs-Markov models,
[Abstract],
in Computing Science and
Statistics: Proceedings of the 27th Symposium on the Interface,
Interface Foundation, 1995.
- J. Lafferty and B. Suhm,
Cluster expansions and iterative scaling of
maximum entropy language models, [Abstract]
in Fifteenth International Workshop on Maximum Entropy and
Bayesian Methods,
Kluwer Academic Publishers, 1995.
- J. Lafferty, S. Della Pietra, and V. Della Pietra,
Inducing features of random fields,
[Abstract],
IEEE Transactions on
Pattern Analysis and Machine Intelligence, 19(4), April 1997,
pp. 380-393.
- D. Grinberg, J. Lafferty and D. Sleator,
A robust parsing algorithm for link
grammars, [Abstract],
Proceedings of the Fourth International Workshop on Parsing
Technologies, Prague and Karlovy Vary, September 1995, pp. 111-125.
Also issued as technical report CMU-CS-95-125, Department of Computer
Science, Carnegie Mellon University, 1995.
- S. Della Pietra, V. Della Pietra, J. Gillett, J. Lafferty, H. Printz,
L. Ures,
Inference and estimation of a long-range trigram model,
[Abstract],
Proceedings of the Second International Colloquium on Grammatical
Inference and Applications, Lecture Notes in Artificial Intelligence,
862, Springer-Verlag, 78-92, 1994.
Also issued as technical report CMU-CS-94-188, Department of
Computer Science, Carnegie Mellon University, 1992.
- A. Berger, P. Brown, S. Della Pietra, V. Della Pietra, J. Gillett, J.
Lafferty, R. Mercer, H. Printz, and L. Ures,
The Candide system for machine translation,
[Abstract],
in Human Language Technology: Proceedings of the
ARPA Workshop on Speech and Natural Language, Morgan Kaufman
Publishers, 1994.
- J. Lafferty, D. Sleator, and D. Temperley,
Grammatical trigrams: A
probabilistic model of link grammar,
[Abstract],
in Proceedings of the AAAI Fall
Symposium on Probabilistic Approaches to Natural Language, Cambridge, MA,
October 1992. Also issued as technical report CMU-CS-92-181, Department of
Computer Science, Carnegie Mellon University, 1992.
- D. Sleator, and D. Temperley, Parsing
English with a link grammar,
[Abstract], technical report
CMU-CS-91-196, Department of Computer Science, Carnegie Mellon
University, 1991. A version of this paper
appears in Proceedings of the Third International Workshop on
Parsing Technologies, 1993.
Funding
This research is funded by NSF and ARPA through a grant
from the NSF Interactive
Systems Program. Additional support is provided by the
School of Computer Science at Carnegie Mellon University.
Dennis Grinberg
dennis+@cs.cmu.edu