shtoshni / fast-coref

Code for the CRAC 2021 paper "On Generalization in Coreference Resolution" (Best short paper award)
33 stars 13 forks source link

Training on litbank dataset #4

Closed aakashb95 closed 2 years ago

aakashb95 commented 2 years ago

I am modifying a few clusters from the litbank dataset. How do I create the jsonlines for my custom litbank dataset like the one you have in your google drive?

And ones I have the jsonlines, then i should run the following right?:

python main.py experiment=litbank trainer.label_smoothing_wt=0.0
shtoshni commented 2 years ago

Modify the CoNLL files for Litbank and then reprocess the data as follows:

python data_processing/process_litbank.py ../../coref_resources/data/litbank/conll

And regarding retraining, yes that's the procedure to train the model.

aakashb95 commented 2 years ago

Thanks for the instructions. Needed some help with the conll files which I was able to get from here.