吴震 - 南京大学 - 人工智能学院

个人简介

Now I am an Associate Researcher 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 News 2023-10-08: Four papers were accepted by EMNLP 2023 (CCF-B). 2023-09-23: We won the runner-up of the Evaluation of Large Model of Finance Technology (SMP2023-ELMFT) out of 2294 teams. 2023-07-26: Two papers were accepted by ACM Multimedia 2023 (CCF-A). 2023-05-02: Two papers were accepted by main conference and findings of ACL 2023 (CCF-A). 2023-02-17: One paper was accepted by ICASSP 2023 (CCF-B). 2022-10-14: One paper was accepted by Science China Information Sciences (CCF-A中文). 2022-10-08: One paper was accepted by Findings of EMNLP 2022. 2022-08-17: Three papers were accepted by COLING 2022 (CCF-B). 2022-06-30: One paper was accepted by ACM Multimedia 2022 (CCF-A). 2021-12-02: One paper was accepted by Frontiers of Computer Science. 2021-03-10: UniDrop was accepted by NAACL 2021. 2020-10-01: ATN was accepted by COLING 2020. 2020-09-14: GTS was accepted by EMNLP 2020 Findings. 2020-07-30: Two papers were accepted by NLPCC 2020. 2020-06-02: Wins the Second Place of NLPCC 2020 Shared Task 2: Multi-Aspect-based Multi-Sentiment Analysis (MAMS) 2019-11-11: LOTN was accepted by AAAI 2020. 2019-07-30: Wins the Third Prize (Top5) of the Evaluation of Chinese Implicit Sentiment Analysis in the 8th National Conference on Socail Media Processing. 2019-02-22: TOWE was accepted by NAACL 2019. 2018-12-05: Wins the Champion of Aspects and Sentiment Recognition of Automotive Industry task (Top1/1701) and CCF Best Innovation Award in CCF BDCI 2018. 2017-11-08: HUAPA was accepted by AAAI 2018.

研究领域

My recent research interest mainly includes sentiment analysis, opinion mining, sentiment generation, multimodal information extraction, and dialogue.

近期论文

查看导师新发文章（温馨提示：请注意重名现象，建议点开原文通过作者单位确认）

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 Summary: UniDrop integrated various dropout techniques and effectively improved Transformer performance.(Oral) NAACL-HLT, 2021. Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction Zhen Wu, Chengcan Ying, Fei Zhao, Zhifang Fan, Xinyu Dai, Rui Xia Summary: A poweful and unified tagging scheme to address fine-grained opinion extraction in the form of opinion pair or opinion triplet.EMNLP Findings, 2020. Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction Zhen Wu*, Fei Zhao*, Xin-Yu Dai, Shujian Huang, Jiajun Chen Summary: Transter opinion knowledge from resource-rich document-level data to improve target-oriented opinion words extraction.(Oral) AAAI, 2020. Attention Transfer Network for Aspect-level Sentiment Classification Fei Zhao*, Zhen Wu*, Xin-Yu Dai Summary: Transter opinion knowledge from resource-rich document-level data to improve aspect-level sentiment classification.COLING, 2020. Transformer-based Multi-Aspect Modeling for Multi-Aspect Multi-Sentiment Analysis Zhen Wu*, Chengcan Ying*, Xinyu Dai, Shujian Huang, Jiajun Chen Summary: A simple yet effective method to improve and accelerate multi-aspect multi-sentiment classification.NLPCC Evaluation, 2020. Opinion Transmission Network for Jointly Improving Aspect-oriented Opinion Words Extraction and Sentiment Classification Chengcan Ying*, Zhen Wu*, Xinyu Dai, Shujian Huang, Jiajun Chen Summary: A joint method to improve both target-oriented opinion words extraction and aspect-level sentiment classification.NLPCC, 2020. Target-oriented Opinion Words Extraction with Target-fused Neural Sequence Labeling Zhifang Fan, Zhen Wu, Xin-Yu Dai, Shujian Huang, Jiajun Chen Summary: Proposed a new ABSA subtask Target-oriented Opinion Words Extraction and released the datasets of opinion pair (aspect term, opinion term).(Oral) NAACL-HLT, 2019. Improving Review Representations with User Attention and Product Attention for Sentiment Classification Zhen Wu, Xin-Yu Dai, Cunyan Yin, Shujian Huang, Jiajun Chen Summary: Modeling reviews respectively from user's perspective and product's perspective.(Oral) AAAI, 2018. Improving aspect identification with reviews segmentation Tianhao Ning, Zhen Wu, Jiajun Huang, Shujian Huang, Jiajun Chen Summary: A self-enhancement method based on reviews segmentation.NLPCC, 2018.