Maarten de Rijke院士学术报告会-山大金沙平台网站学院
Maarten de Rijke院士学术报告会

告知时 5月21日15:00-16:00

Maarten de Rijke院士学报告会



题材:Unbiased Learning to Rank from User Interactions

告知人:Maarten de Rijke授课,荷兰阿姆斯特丹大学

内容:Learning to rank is a core ingredient of search engines, recommender systems, and digital assistants. Supervised approaches to learning to rank are limited in that Annotations often disagree with user preferences.  User interactions solve this problem but bring noise and biases. Counter-factual approaches allow for unbiased learning to rank: if an accurate user model can be learned, we can adjust for biases; we only require randomization to infer a user model. In contrast, online approaches allow for unbiased and responsive learning to rank, as they immediately adapt to user behavior and perform randomization at each step, though limited. Clearly, different situations suit different approaches. We report on recent advances and on recent findings on comparing the two families of approaches.

告知人简介:Maarten de Rijke,荷兰皇家艺术和科学院院士,荷兰阿姆斯特丹大学讲课,荷兰国家人工智能创新中心(Innovation Center for Artificial Intelligence)创始人和领导。重要研究领域包括自然语言处理、信息检索、文化挖掘等。Maarten de Rijke授课目前还领导正在世界著名的 Information Language Processing and System(ILPS) 实验室。他在自语言处理、信息检索、机器学习和数据挖掘的头号会议和杂志上共同上了 800 余 首文章,特别是在家发现(expert finding), 在线学习(online learning), 模态逻辑(modal logic)和问答系统(question-answering) 天地做出了杰出贡献。根据谷歌学术的统计,他脚下的论文引用量超过2万次, h-index 69。Maarten de Rijke 授课多次任信息检索领域各种会议的大会或程序委员会主席,其中包括SIGIR, WWW, WSDM CIKM。Maarten de Rijke授课目前为是多只人工智能领域的头号期刊的主编,其中包括ACM Transactions on Information Systems (TOIS, 华夏计算机学会A接近期刊)Foundations and Trends in Information Retrieval相当。2017 年取得代表国际信息检索领域终身成就的 Tony Kent Strix 奖。