After do_predict for NER, there will be one test_results.txt containing f1 and precision.
While I can get another version of results containing different f1 and accuracy with conlleval.py.
Which should I use ? Which one is the results from paper?
Thanks a lot.
After do_predict for NER, there will be one
test_results.tx
t containingf1
andprecision
. While I can get another version of results containing differentf1
andaccuracy
withconlleval.py
.Which should I use ? Which one is the results from paper? Thanks a lot.