cambridgeltl/mirror-bert
[EMNLP'21] Mirror-BERT: Converting Pretrained Language Models to universal text encoders without labels.
PythonMIT
Issues
- 2
Results for English STS using BERT-mp
#6 opened by zhujiatong628 - 1
- 2
Codes for calculating the isotropy score?
#3 opened by longkukuhi - 3
erase_and_mask masking sub-words
#2 opened by muelletm