search

nanguoshun / LSR

Pytorch Implementation of our ACL 2020 Paper "Reasoning with Latent Structure Refinement for Document-Level Relation Extraction"
127 stars 22 forks source link

Questions about Theta #25

Closed ssppff closed 3 years ago

ssppff commented 4 years ago

Hello, thank you for sharing. What does Theta stand for in training? When I was doing my experiments, Theta was always high, up to 0.9, and I didn't change the Theta part of the code. How do you keep Theta stable during training? Thank you.

nanguoshun commented 3 years ago

hi @ssppff, thanks for your question. Theta here acts as a threshold. we directly use the code from the original repo repohttps://github.com/thunlp/DocRED/blob/master/code/config/Config.py.