CS 8995 Corpus Based Natural Language Processing
Final Project: Empirical Methods for Multilingual Text
Stage 1 - Evaluation Program, as submitted by each team 3/26
Download all of the evaluation programs and run your alignment program on
each of the gold standard data sets. Then evaluate your results on each of
the gold standard data sets using each of the evaluation programs. You
should end up with 49 different scores, based on 7 different sets of gold
standard data and 7 different evaluation programs.
Send me these results via email before midnight, Tue 3/27.
Report them in a format such as this:
RESULTS FOR PACHUCA alignment program
RUNNING ON CRUZ AZUL data
CRUZ AZUL x
TOLUCA x
MORELIA x
UNAM x
PACHUCA x
TIGRES x
PUEBLA x
RUNNING ON TOLUCA data
CRUZ AZUL x
TOLUCA x
MORELIA x
UNAM x
PACHUCA x
TIGRES x
PUEBLA x
etc.
by:
Ted Pedersen
- tpederse@d.umn.edu