Zihang Jiang

LV-BERT: Exploiting Layer Variety for BERT

2021 · arXiv (Cornell University)

Modern pre-trained language models are mostly built upon backbones stacking self-attention and feed-forward layers in an interleaved order. In this paper, beyond this stereotyped layer pattern, we aim to improve pre-trained models by exploiting layer …

ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning

2020 · arXiv (Cornell University)

Recent powerful pre-trained language models have achieved remarkable performance on most of the popular datasets for reading comprehension. It is time to introduce more challenging datasets to push the development of this field towards more …

ConvBERT: Improving BERT with Span-based Dynamic Convolution

2020 · arXiv (Cornell University)

Pre-trained language models like BERT and its variants have recently achieved impressive performance in various natural language understanding tasks. However, BERT heavily relies on the global self-attention block and thus suffers large memory footprint and …