The dopdis project (version 1.0)


Last updated 21 Jan 2008: version 1.0.
Previous release (version 0.1) was 10 Jan 2005.
Khalil Sima'an

THIS CODE IS NOT BEING MAINTAINED.
USE AS IS AND WHEN SUCCESSFUL PLEASE REFER TO THE FOLLOWING PAPERS:
  1. THIS CODE:  K. Sima'an. An Optimized Algorithm for Data-Oriented Parsing. In proceedings of International Conference on Recent Advances in Natural Language Processing (RANLP'95). Tzigov Chark. Bulgaria, 1995.
  2. DOP IN GENERAL: R. Bod, R. Scha and K. Sima'an (editors). Data-Oriented Parsing (edited volume)  Studies in Computational Linguistics, CSLI  Publications, University of Chicago Press, 2003.
  3. DOP*: A.  Zollmann and K. Sima'an.     A Consistent and Efficient Estimator for Data-Oriented Parsing.
    Journal of Automata, Languages and Combinatorics (JALC)  Vol. 10 (2005) Number 2/3, pages 367-388

The dopdis parsing environment encompasses a trainable DOP1 parser, an implementation of the DOP* estimator, as well as tools for viewing and splitting treebanks and evaluating trained DOP parsers. The project has been written for the Linux (RedHat) platform and is distributed under the GNU public license (GPL)

The main scientific reference for the dopdis parser is this document.  Many usefull references for work on DOP can be found in this book.
Further links to relevant literature on Data-Oriented Parsing (DOP) can be found in the listings maintained here and here.
Confer also the bibliography listed in the user's manual.




HOME, yeah! Back to homepage of Khalil Sima'an