Dan Melamed's NLP Research Software Library
Bitext Geometry Section

Copyright (C) 1996 by I. Dan Melamed

This library is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation.


This library is distributed in the hope that it will
a) reduce the amount of time that researchers waste writing and debugging software that already exists elsewhere,
b) reduce the "start-up time" for people who are just getting acquainted with empirical methods in NLP,
c) demonstrate how common NLP programming languages, like Perl and awk, can be used to construct useful tools.
However, the library is being distributed WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.


The file DESCRIPTIONS contains one-line descriptions of what each program does, in cases where that's not obvious from the program's name.

To download this entire library section at once, get the file ALL.tar.gz.

To grab individual files look here.

Note that many of the programs assume that you have the usual Unix tools installed in the usual places. If you don't, then you may have to acquire them or change the hard-wired path specification at the top of the source file of interest.

If you want to learn more about bitext geometry, read
I. Dan Melamed, A Geometric Approach to Mapping Bitext Correspondence, IRCS Technical Report #96-22, a revised version of the paper presented at the Conference on Empirical Methods in Natural Language Processing (EMNLP'96), Philadelphia, PA, May 1996.

Back to Dan Melamed's HomePage