# BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification Context

25 Sep 2020

Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability... (read more)

PDF Abstract