Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks
Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation
Label Semantic Aware Pre-training for Few-shot Text Classification
A Simple Recipe for Multilingual Grammatical Error Correction
Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction
Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding