facebookresearch/SentAugment
SentAugment is a data augmentation technique for NLP that retrieves similar sentences from a large bank of sentences. It can be used in combination with self-training and knowledge-distillation, or for retrieving paraphrases.
PythonNOASSERTION
Issues
- 0
The URL is not working
#15 opened by e0397123 - 1
GPU Memory issue in using Faiss index
#14 opened by Amit-GH - 1
- 0
Question about Roberta-small size
#11 opened by MatthewCYM - 1
- 0
Hello, I read your paper, but I didn’t see the difference between this idea and distant supervision
#10 opened by mlyzy - 1
- 0
High RAM usage during sentence encoding
#6 opened by LukasDBaker - 2
Hello, I read the paper and think that the 'Self-training' is similar to 'Knowledge-Distillation'。What‘s the difference between them? Thanks.
#5 opened by lbda1 - 5
Kernel dies during embedding of sentences
#4 opened by avinashsai - 1
indexTextQuery
#2 opened by luolanfeixue - 1
some codes are missing
#1 opened by luolanfeixue