facebookresearch / bio-lm

We evaluate many models used for biomedical and clinical nlp tasks, and train new models that perform much better.
Other
157 stars 24 forks source link

For NER, Difference between test_results.txt and conlleval.py results ? #16

Open zwd2080 opened 2 years ago

zwd2080 commented 2 years ago

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.