基本信息
曹逸轩 男 硕导 中国科学院计算技术研究所
电子邮件： caoyixuan@ict.ac.cn
通信地址： 科学院南路6号
邮政编码： 100190
电子邮件： caoyixuan@ict.ac.cn
通信地址： 科学院南路6号
邮政编码： 100190
研究领域
文档智能处理、自然语言处理、专业文档信息抽取、机器学习
招生信息
招生专业
081202-计算机软件与理论
085400-电子信息
085400-电子信息
招生方向
机器学习,自然语言处理
教育背景
2015-09--2020-09 中国科学院计算技术研究所 博士
工作经历
工作简历
2022-11~现在, 中国科学院计算技术研究所, 副研究员
2020-10~2022-11,中国科学院计算技术研究所, 特别研究助理
2020-10~2022-11,中国科学院计算技术研究所, 特别研究助理
出版信息
发表论文
[1] 庞朝旭, 曹逸轩, 杨春昊, 罗平. Uncovering Limitations of Large Language Models in Information Seeking from Tables. Findings of ACL. 2024, 第 2 作者
[2] Chanxu Pang, Yixuan CAO, Qiang Ding, Ping LUO. Guideline Learning for In-context Information Extraction. EMNLP. 2023, 第 2 作者 通讯作者
[3] Qiang Ding, Yixuan CAO, Ping LUO. Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification. NeurIPS. 2023, 第 2 作者
[4] Qingping Yang, Yixuan Cao, Ping LUO. Numerical Tuple Extraction from Tables with Pre-training. KDD. 2022, 第 2 作者
[5] Cao, RongYu, Cao, YiXuan, Zhou, GanBin, Luo, Ping. Extracting Variable-Depth Logical Document Hierarchy from Long Documents: Method, Evaluation, and Application. Journal of Computer Science and Technology[J]. 2022, 第 2 作者37(3): 699-718, http://dx.doi.org/10.1007/s11390-021-1076-7.
[6] Hongwei LI, Yingpeng HU, Yixuan CAO, Ganbin ZHOU, Ping LUO. Rich-text document styling restoration via reinforcement learning. Frontiers of Computer Science[J]. 2021, 第 3 作者15(4): 93-103, http://lib.cqvip.com/Qikan/Article/Detail?id=7105304038.
[7] Qingping Yang, Yixuan Cao, Ping Luo. Numerical Formula Recognition from Tables. The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2021, 第 2 作者
[8] Cao, Yixuan, Chen, Dian, Xu, Zhengqi, Li, Hongwei, Luo, Ping. Nested relation extraction with iterative neural network. Frontiers of Computer Science[J]. 2021, 第 1 作者15(3): 109-122, http://lib.cqvip.com/Qikan/Article/Detail?id=7105031502.
[9] 曹逸轩, 洪峰, 李宏伟, 罗平. A Bottom-Up DAG Structure Extraction Model for Math Word Problems. AAAI. 2021, 第 1 作者
[10] Hongwei Li, Yingpeng Hu, Yixuan Cao, Ganbin Zhou, Ping Luo. Rich-text Document Styling Restoration via Reinforcement Learning. Frontiers of Computer Science[J]. 2021, 第 3 作者
[11] 徐政奇, 曹逸轩. Jura: Towards Automatic Compliance Assessment for Annual Reports of Listed Companies. CIKM. 2021, 第 2 作者
[12] Dian Chen, Yixuan Cao, Ping Luo. Pairwise Causality Structure Towards Nested Causality Mining on Financial Statements. NLPCC. 2020, 第 2 作者
[13] Hongwei Li, Qingping Yang, Yixuan Cao, Jiaquan Yao, Ping Luo. Cracking Tabular Presentation Diversity for Automatic Cross-Checking over Numerical Facts. KDD. 2020, 第 3 作者
[14] Li, Hongwei, Yang, Qingping, Cao, Yixuan, Zhou, Ganbin, Luo, Ping. Semantic Matching over Matrix-Style Tables in Richly Formatted Documents. DEXA. 2020, 第 3 作者12391: 369-384,
[15] Cao, Yixuan, Chen, Dian, Li, Hongwei, Luo, Ping. Nested Relation Extraction with Iterative Neural Network. PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19). 2019, 第 1 作者1001-1010, http://dx.doi.org/10.1145/3357384.3358003.
[16] Cao, Yixuan, Li, Hongwei, Luo, Ping, Yao, Jiaquan. Towards Automatic Numerical Cross-Checking: Extracting Formulas from Text. WEB CONFERENCE 2018: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW2018). 2018, 第 1 作者1795-1804, http://dx.doi.org/10.1145/3178876.3186166.
[2] Chanxu Pang, Yixuan CAO, Qiang Ding, Ping LUO. Guideline Learning for In-context Information Extraction. EMNLP. 2023, 第 2 作者 通讯作者
[3] Qiang Ding, Yixuan CAO, Ping LUO. Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification. NeurIPS. 2023, 第 2 作者
[4] Qingping Yang, Yixuan Cao, Ping LUO. Numerical Tuple Extraction from Tables with Pre-training. KDD. 2022, 第 2 作者
[5] Cao, RongYu, Cao, YiXuan, Zhou, GanBin, Luo, Ping. Extracting Variable-Depth Logical Document Hierarchy from Long Documents: Method, Evaluation, and Application. Journal of Computer Science and Technology[J]. 2022, 第 2 作者37(3): 699-718, http://dx.doi.org/10.1007/s11390-021-1076-7.
[6] Hongwei LI, Yingpeng HU, Yixuan CAO, Ganbin ZHOU, Ping LUO. Rich-text document styling restoration via reinforcement learning. Frontiers of Computer Science[J]. 2021, 第 3 作者15(4): 93-103, http://lib.cqvip.com/Qikan/Article/Detail?id=7105304038.
[7] Qingping Yang, Yixuan Cao, Ping Luo. Numerical Formula Recognition from Tables. The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2021, 第 2 作者
[8] Cao, Yixuan, Chen, Dian, Xu, Zhengqi, Li, Hongwei, Luo, Ping. Nested relation extraction with iterative neural network. Frontiers of Computer Science[J]. 2021, 第 1 作者15(3): 109-122, http://lib.cqvip.com/Qikan/Article/Detail?id=7105031502.
[9] 曹逸轩, 洪峰, 李宏伟, 罗平. A Bottom-Up DAG Structure Extraction Model for Math Word Problems. AAAI. 2021, 第 1 作者
[10] Hongwei Li, Yingpeng Hu, Yixuan Cao, Ganbin Zhou, Ping Luo. Rich-text Document Styling Restoration via Reinforcement Learning. Frontiers of Computer Science[J]. 2021, 第 3 作者
[11] 徐政奇, 曹逸轩. Jura: Towards Automatic Compliance Assessment for Annual Reports of Listed Companies. CIKM. 2021, 第 2 作者
[12] Dian Chen, Yixuan Cao, Ping Luo. Pairwise Causality Structure Towards Nested Causality Mining on Financial Statements. NLPCC. 2020, 第 2 作者
[13] Hongwei Li, Qingping Yang, Yixuan Cao, Jiaquan Yao, Ping Luo. Cracking Tabular Presentation Diversity for Automatic Cross-Checking over Numerical Facts. KDD. 2020, 第 3 作者
[14] Li, Hongwei, Yang, Qingping, Cao, Yixuan, Zhou, Ganbin, Luo, Ping. Semantic Matching over Matrix-Style Tables in Richly Formatted Documents. DEXA. 2020, 第 3 作者12391: 369-384,
[15] Cao, Yixuan, Chen, Dian, Li, Hongwei, Luo, Ping. Nested Relation Extraction with Iterative Neural Network. PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19). 2019, 第 1 作者1001-1010, http://dx.doi.org/10.1145/3357384.3358003.
[16] Cao, Yixuan, Li, Hongwei, Luo, Ping, Yao, Jiaquan. Towards Automatic Numerical Cross-Checking: Extracting Formulas from Text. WEB CONFERENCE 2018: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW2018). 2018, 第 1 作者1795-1804, http://dx.doi.org/10.1145/3178876.3186166.
科研活动
科研项目
（ 1 ） 面向关键任务的可信信息抽取, 负责人, 国家任务, 2023-01--2025-12
（ 2 ） 富文档中的知识发现和信息抽取研究, 参与, 国家任务, 2021-01--2024-12
（ 3 ） 新型链上数字内容的安全智能监管关键技术, 参与, 国家任务, 2022-11--2025-10
（ 2 ） 富文档中的知识发现和信息抽取研究, 参与, 国家任务, 2021-01--2024-12
（ 3 ） 新型链上数字内容的安全智能监管关键技术, 参与, 国家任务, 2022-11--2025-10