Skip to content

Latest commit

 

History

History
18 lines (14 loc) · 515 Bytes

README.md

File metadata and controls

18 lines (14 loc) · 515 Bytes

STER

PyTorch code for "Exploring Privileged Features for Relation Extraction with Contrastive Student-Teacher Learning"

Requirements

  • Required
    • Python 3.6
    • PyTorch 1.3.1
    • transformers 2.2.0
    • scikit-learn 0.21.3
    • tqdm 4.19.5
    • numpy 1.17.4

Datasets

To obtain the CoNLL04, SciERC and ADE datasets, please read the details provided here.

Acknowledgments

Our code is built based on SpERT.