helloeve / mre-in-one-pass

Implementation for Extracting Multiple-Relations in One-Passwith Pre-Trained Transformers
Apache License 2.0
80 stars 20 forks source link

Unable to locate the entity aware self attention code #6

Closed VishalPallagani closed 4 years ago

VishalPallagani commented 4 years ago

I am trying to implement just the entity aware self-attention module of the paper and I cannot locate it in the run_classifier.py code. I will be grateful if someone can point me at the self-attention implementation code so I can get my work started. Thanks in advance.

helloeve commented 4 years ago

@VishalPallagani please check the implementation in modeling.py for the entity aware self-attention model - https://github.com/helloeve/mre-in-one-pass/blob/master/modeling.py#L560-L764