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

Link Grammar Homepage

This page describes the underlying parsing technology that the project is developing. It includes background information and an on-line demonstration of the system.



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