Code for assignments from prof. Michael Collin's NLP course, COMSW4705 Spring 2015 at Columbia U.
See report.pdf for description and instructions.
The files given by prof. Collins should be placed in the same directory as my scripts for a successful execution.
=================================================== Files given by prof. Collins
count_cfg_freq.py
eval_parser.py
parse_dev.dat
parse_dev.key
parse_train_vert.dat
parse_train.dat
pretty_print_tree.py
=================================================== My python scripts: relabel_rare.py
utils.py
cyk.py
=================================================== Counts for parse_train.dat, parse_train_vert.dat, to be obtained after running relabel_rare.py to replace rare words.
cfg_vert.counts cfg.counts