2 papers
cs.CL2022
Probing Script Knowledge from Pre-Trained Models
Zijian Jin, Xingyu Zhang, Mo Yu +1
Script knowledge is critical for humans to understand the broad daily tasks and routine activities in the world. Recently researchers have explored the large-scale pre-trained lang…
cs.CL2022
Efficient Long Sequence Encoding via Synchronization
Xiangyang Mou, Mo Yu, Bingsheng Yao +1
Pre-trained Transformer models have achieved successes in a wide range of NLP tasks, but are inefficient when dealing with long input sequences. Existing studies try to overcome th…