赵广振

发布时间:2026-05-26浏览次数:10文章来源:U8集团

姓名:赵广振
职称:讲师
部门:U8集团
赵广振,博士,2024年3月毕业于东南大学计算机科学与工程公司,现任U8集团讲师。主要研究方向为自然语言处理、表格型数据可信问答和大语言模型推理。重点关注表格型证据条件下的事实验证、复杂证据推理、神经与符号协同核验以及多表推理智能体的运行时可信性问题。
赵广振
学术成果
赵广振博士长期围绕结构化数据环境中的可信推理开展研究。以第一作者身份在ACL、EMNLP、COLING等CCF A/B类会议和ACM Transactions on Information Systems(CCF A类期刊)等发表论文6篇,以参与作者在软件学报(CCF中文A类)、IEEE TNNLS、IEEE/ACM TASLP(CCF B类期刊)等发表论文3篇。获授权发明专利1项。指导员工获NDBC 2025优秀员工论文奖。
代表性文章
1. Guangzhen Zhao, Dechang Kong, Tongyu Wu, Zhenjiang Dong. TrustTable: A Neuro-Symbolic Auditing Framework for Faithful Table QA[C]//Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics. 2026.(第一作者,CCF A类会议,已录用)
2. Guangzhen Zhao, Yu Yao, Dechang Kong, Zhenjiang Dong. Seeking Rational Demonstrations for Large Language Models: A Domain Generalization Approach to Unsupervised Cross-Domain Keyphrase Generation[C]//Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics. 2025: 414-424.(第一作者,CCF A类会议)
3. Guangzhen Zhao, Peng Yang. Pretrained Embeddings for Stance Detection with Hierarchical Capsule Network on Social Media[J]. ACM Transactions on Information Systems, 2020, 39(1): 1-32.(第一作者,CCF A类期刊)
4. Guangzhen Zhao, Guoshun Yin, Peng Yang, Yu Yao. Keyphrase Generation via Soft and Hard Semantic Corrections[C]//Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022: 7757-7768.(第一作者,CCF B类会议)
5. Guangzhen Zhao, Peng Yang. Table-based Fact Verification with Self-labeled Keypoint Alignment[C]//Proceedings of the 29th International Conference on Computational Linguistics. 2022: 1401-1411.(第一作者,CCF B类会议)
6. Guangzhen Zhao, Peng Yang, Yu Yao. RERG: Reinforced Evidence Reasoning with Graph Neural Network for Table-based Fact Verification[J]. Applied Intelligence, 2023, 53(10): 12308-12323.(第一作者,SCI Q2)
7. 杨鹏,查显宇,赵广振,林茜. 基于胶囊异构图注意力网络的中文表格型数据事实验证[J]. 软件学报,2024,35(9): 4324-4345.(参与作者,CCF中文A类期刊)
8. Yu Yao, Peng Yang, Guangzhen Zhao, Yanyan Ge, Ying Yang. Probabilistic Keyphrase Generation From Copy and Generating Spaces[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(11): 15956-15970.(参与作者,CCF B类期刊)
9. Yu Yao, Peng Yang, Guangzhen Zhao, Guoshun Yin. KGAgent: Learning a Deep Reinforced Agent for Keyphrase Generation[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024, 32: 1928-1940.(参与作者,CCF B类期刊)
学术活动
中国计算机学会(CCF)专业会员,中文信息学会专业会员,CCF数据库专委会会员,CCF自然语言处理专委会会员。担任Knowledge Based System、IEEE Transactions on Neural Networks and Learning Systems、ACM Transactions on Management Information Systems、Applied Intelligence 、AAAI、ACL ARR、KDD、WWW等期刊或者会议审稿人。
获奖
集成多推理范式的表格问答方法研究,第42届CCF中国数据库学术会议(NDBC 2025). (优秀员工论文奖)
项目
U8集团校级自然科学基金项目:面向表格型证据的事实核查研究,编号:NY225024,起止时间:2025.05–2028.04,在研