Zhen Wu (吴震)
School of Artificial Intelligence, Nanjing University (NJU)
Address: 163 Xianlin Avenue, Qixia District, Nanjing, China
Office: Room A-201, Yifu Building
Email: wuz [at] nju.edu.cn

About Me [Google Scholar]

Now I am an Assistant Professor at the School of Artificial Intelligence, Nanjing University (NJU), and a member of NJUNLP group, led by Prof. Jiajun Chen. Before that, I received my Ph.D. degree from the Department of Computer Science and Technology of Nanjing University (NJU) in 2021, supervised by Prof. Xinyu Dai.

Research Interest

My recent research interests mainly include emotional intelligence, multimodal computation, and large language models.


Selected Publications ([Full List])

(* indicates equal contribution)
UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost
Zhen Wu, Lijun Wu, Qi Meng, Yingce Xia, Shufang Xie, Tao Qin, Xinyu Dai, Tie-Yan Liu
NAACL-HLT, 2021 (oral presentation)
[Paper] [中文解读] [Slides] [Poster] [BibTex]
UniDrop integrated different dropout techniques and effectively improved Transformer performance.
Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction
Zhen Wu, Chengcan Ying, Fei Zhao, Zhifang Fan, Xinyu Dai, Rui Xia
EMNLP Findings, 2020
[Paper] [Datasets and Code] [中文解读] [BibTex]
We propose a unified tagging scheme to address fine-grained opinion extraction, in the form of opinion pair (aspect term, opinion term) or opinion triplet (aspect term, opinion term, sentiment).
Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction
Zhen Wu*, Fei Zhao*, Xin-Yu Dai, Shujian Huang, Jiajun Chen
AAAI, 2020 (oral presentation)
[Paper] [Code] [中文解读] [BibTex]
We transter opinion knowledge from resource-rich document-level data to improve target-oriented opinion words extraction.
Attention Transfer Network for Aspect-level Sentiment Classification
Fei Zhao*, Zhen Wu*, Xin-Yu Dai
COLING, 2020
[Paper] [Code] [中文解读] [BibTex]
We transter opinion knowledge from resource-rich document-level data to improve aspect-level sentiment classification.
Transformer-based Multi-Aspect Modeling for Multi-Aspect Multi-Sentiment Analysis
Zhen Wu*, Chengcan Ying*, Xinyu Dai, Shujian Huang, Jiajun Chen
NLPCC Evaluation, 2020
[Paper] [Code] [BibTex]
A simple yet effective method to improve and accelerate multi-aspect multi-sentiment classification.
Opinion Transmission Network for Jointly Improving Aspect-oriented Opinion Words Extraction and Sentiment Classification
Chengcan Ying*, Zhen Wu*, Xinyu Dai, Shujian Huang, Jiajun Chen
NLPCC, 2020
[Paper] [BibTex]
A joint method to improve both target-oriented opinion words extraction and aspect-level sentiment classification.
Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling
Zhifang Fan, Zhen Wu, Xin-Yu Dai, Shujian Huang, Jiajun Chen
[Paper] [Datasets and Code] [中文解读] [Talk] [BibTex]
We proposed a new ABSA subtask Target-oriented Opinion Words Extraction and released the datasets. We are the first to annotate the datasets of opinion pair (aspect term, opinion term).
Improving Review Representations with User Attention and Product Attention for Sentiment Classification
Zhen Wu, Xin-Yu Dai, Cunyan Yin, Shujian Huang, Jiajun Chen
AAAI, 2018 (oral presentation)
[Paper] [Code] [Poster] [BibTex]
Modeling reviews respectively from user's perspective and product's perspective.


  • Aug. 2020 - Mar. 2021, research intern at Microsoft Research Asia, supervised by Lijun Wu and Tao Qin


  • National Scholarship, 2020.
  • NLPCC 2020 Shared Task, Multi-Aspect-based Multi-Sentiment Analysis (MAMS), 2020, Second Place.
  • Evaluation of Chinese Implicit Sentiment Analysis in the 8th National Conference on Social Media Processing, 2019, Third Prize (Top5).
  • CCF Big Data & Computing Intelligence Contest, "Aspects and Sentiment Recognition of Automotive Industry" Task, 2018, Champion (Top1/1701).
  • CCF Big Data & Computing Intelligence Contest, 2018, Best Innovation Award.
  • Artificial Intelligence Scholarship, 2018, Nanjing University.

Review Services

Program Committee Member/Conference Reviewer
Neural Information Processing Systems (NeurIPS), 2022
International Conference on Machine Learning (ICML), 2022
AAAI Conference on Artificial Intelligence (AAAI), 2021, 2022
Annual Meeting of the Association for Computational Linguistics (ACL), 2021, 2022
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021, 2022
International Conference on Computational Linguistics (COLING), 2020, 2022
China National Conference on Computational Linguistics (CCL), 2021
International Workshop on Natural Language Processing for Social Media (SocialNLP), 2021

Journal Reviewer
TKDD, TALLIP, Neurocomputing