activity
20182022
most citedAutoRC: Improving BERT Based Relation Classification Models via Architecture Search

5 citations · 14 across the 8 of their papers we have counts for

collaborators

12 papers

cs.LG2022

Localized Adversarial Domain Generalization

Wei Zhu, Le Lu, Jing Xiao +3

Deep learning methods can struggle to handle domain shifts not seen in training data, which can cause them to not generalize well to unseen domains. This has led to research attent…

cs.CL2022

A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation

Tianxiang Sun, Xiangyang Liu, Wei Zhu +7

Early exiting allows instances to exit at different layers according to the estimation of difficulty. Previous works usually adopt heuristic metrics such as the entropy of internal…

cs.LG2021

Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization

Wei Zhu, Haitian Zheng, Haofu Liao +2

Deep learning algorithms mine knowledge from the training data and thus would likely inherit the dataset's bias information. As a result, the obtained model would generalize poorly…

cs.CL20213 cited

Lex-BERT: Enhancing BERT based NER with lexicons

Wei Zhu, Daniel Cheung

In this work, we represent Lex-BERT, which incorporates the lexicon information into Chinese BERT for named entity recognition (NER) tasks in a natural manner. Instead of using wor…

cs.CL2020

CMV-BERT: Contrastive multi-vocab pretraining of BERT

Wei Zhu, Daniel Cheung

In this work, we represent CMV-BERT, which improves the pretraining of a language model via two ingredients: (a) contrastive learning, which is well studied in the area of computer…

cs.CL20204 cited

MVP-BERT: Redesigning Vocabularies for Chinese BERT and Multi-Vocab Pretraining

Wei Zhu

Despite the development of pre-trained language models (PLMs) significantly raise the performances of various Chinese natural language processing (NLP) tasks, the vocabulary for th…