-
Put
EventStoryLine
,CausalTM
,EventCausalityData
,SemEval
, andFrameNet
datasets in the current directory. -
Run
read_document.py
to build all intra-sentence examples forEventStoryLine
. -
Run
preprecess_*.py
to generate BERT-based examples for difference datasets and settings. -
Run
train_mix.py
to train the model, with different settings.