Timezone: »
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 computation cost. Although all its attention heads query on the whole input sequence for generating the attention map from a global perspective, we observe some heads only need to learn local dependencies, which means existence of computation redundancy. We therefore propose a novel span-based dynamic convolution to replace these self-attention heads to directly model local dependencies. The novel convolution heads, together with the rest self-attention heads, form a new mixed attention block that is more efficient at both global and local context learning. We equip BERT with this mixed attention design and build a ConvBERT model. Experiments have shown that ConvBERT significantly outperforms BERT and its variants in various downstream tasks, with lower training cost and fewer model parameters. Remarkably, ConvBERTbase model achieves 86.4 GLUE score, 0.7 higher than ELECTRAbase, using less than 1/4 training cost. Code and pre-trained models will be released.
Author Information
Zi-Hang Jiang (National University of Singapore)
Weihao Yu (National University of Singapore)
Daquan Zhou (National University of Singapore)
Yunpeng Chen (Yitu Technology)
Jiashi Feng (National University of Singapore)
Shuicheng Yan (National University of Singapore)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Poster: ConvBERT: Improving BERT with Span-based Dynamic Convolution »
Tue Dec 8th 05:00 -- 07:00 AM Room Poster Session 0
More from the Same Authors
-
2020 Poster: Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam in Deep Learning »
Pan Zhou · Jiashi Feng · Chao Ma · Caiming Xiong · Steven Chu Hong Hoi · Weinan E -
2020 Poster: Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts »
Guilin Li · Junlei Zhang · Yunhe Wang · Chuanjian Liu · Matthias Tan · Yunfeng Lin · Wei Zhang · Jiashi Feng · Tong Zhang -
2020 Poster: Improving Generalization in Reinforcement Learning with Mixture Regularization »
KAIXIN WANG · Bingyi Kang · Jie Shao · Jiashi Feng -
2020 Poster: Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation »
Jianfeng Zhang · Xuecheng Nie · Jiashi Feng -
2019 Poster: Efficient Meta Learning via Minibatch Proximal Update »
Pan Zhou · Xiaotong Yuan · Huan Xu · Shuicheng Yan · Jiashi Feng -
2019 Poster: Heterogeneous Graph Learning for Visual Commonsense Reasoning »
Weijiang Yu · Jingwen Zhou · Weihao Yu · Xiaodan Liang · Nong Xiao -
2019 Spotlight: Heterogeneous Graph Learning for Visual Commonsense Reasoning »
Weijiang Yu · Jingwen Zhou · Weihao Yu · Xiaodan Liang · Nong Xiao -
2019 Spotlight: Efficient Meta Learning via Minibatch Proximal Update »
Pan Zhou · Xiaotong Yuan · Huan Xu · Shuicheng Yan · Jiashi Feng -
2018 Poster: New Insight into Hybrid Stochastic Gradient Descent: Beyond With-Replacement Sampling and Convexity »
Pan Zhou · Xiaotong Yuan · Jiashi Feng -
2018 Poster: Efficient Stochastic Gradient Hard Thresholding »
Pan Zhou · Xiaotong Yuan · Jiashi Feng -
2018 Poster: A^2-Nets: Double Attention Networks »
Yunpeng Chen · Yannis Kalantidis · Jianshu Li · Shuicheng Yan · Jiashi Feng -
2017 Poster: Dual Path Networks »
Yunpeng Chen · Jianan Li · Huaxin Xiao · Xiaojie Jin · Shuicheng Yan · Jiashi Feng -
2017 Spotlight: Dual Path Networks »
Yunpeng Chen · Jianan Li · Huaxin Xiao · Xiaojie Jin · Shuicheng Yan · Jiashi Feng -
2017 Poster: Multimodal Learning and Reasoning for Visual Question Answering »
Ilija Ilievski · Jiashi Feng -
2017 Poster: Predicting Scene Parsing and Motion Dynamics in the Future »
Xiaojie Jin · Huaxin Xiao · Xiaohui Shen · Jimei Yang · Zhe Lin · Yunpeng Chen · Zequn Jie · Jiashi Feng · Shuicheng Yan -
2017 Poster: Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis »
Jian Zhao · Lin Xiong · Panasonic Karlekar Jayashree · Jianshu Li · Fang Zhao · Zhecan Wang · Panasonic Sugiri Pranata · Panasonic Shengmei Shen · Shuicheng Yan · Jiashi Feng -
2016 Poster: Tree-Structured Reinforcement Learning for Sequential Object Localization »
Zequn Jie · Xiaodan Liang · Jiashi Feng · Xiaojie Jin · Wen Lu · Shuicheng Yan -
2014 Poster: Robust Logistic Regression and Classification »
Jiashi Feng · Huan Xu · Shie Mannor · Shuicheng Yan -
2014 Poster: Convex Optimization Procedure for Clustering: Theoretical Revisit »
Changbo Zhu · Huan Xu · Chenlei Leng · Shuicheng Yan -
2014 Poster: On a Theory of Nonparametric Pairwise Similarity for Clustering: Connecting Clustering to Classification »
Yingzhen Yang · Feng Liang · Shuicheng Yan · Zhangyang Wang · Thomas S Huang -
2013 Poster: Online Robust PCA via Stochastic Optimization »
Jiashi Feng · Huan Xu · Shuicheng Yan -
2013 Poster: Online PCA for Contaminated Data »
Jiashi Feng · Huan Xu · Shie Mannor · Shuicheng Yan