报告题目：Unsupervised Document Summarization via Contrastive Learning

报告人：ZhangWei

报告时间：2024年7月12日10:00 -12:00

报告地点：数统学院4号楼312

邀请单位：福州大学数学与统计学院

报告内容简介：

Document summarization generates concise summaries that preserve core information. It is important for applications like news headlines and medical reports. Due to the challenge of obtaining large-scale, high-quality parallel data for training, unsupervised abstractive summarization is increasingly important, particularly for uncommon domains and languages without sufficient labeled data. We will introduce our method of using contrastive learning for document summarization, exploring negative examples, and leveraging knowledge to enhance summarization model performance.

报告人简介：

Dr Wei Zhang is a Senior Lecturer (equivalent to Associate Professor in the US system) and Associate Head of People and Culture at the School of Computer and Mathematical Sciences, and an academic member of the Australian Institute for Machine Learning, The University of Adelaide, Australia. Dr Zhang currently holds an ARC Early Career Industry Fellowship 2024-2027. Dr Zhang’s research focuses on Document Summarization, Adversarial attack, and Artificial Intelligence of Things.

She has more than 100 publications as edited books and proceedings, refereed book chapters, and refereed technical papers in journals and conferences including ACM CSUR, IEEE COMST, ACM TIST, ACM TOIT, ACM TOSN, WWWJ, CACM, ACL, NAACL, EMNLP, ACM SIGIR, WWW, CIKM, ECCV, and ICSOC. Her work receives academia and industry funding worth > AUD $3M within the recent 5 years, including 3 ARC funding as lead investigator. She has been actively engaged in professional services by serving as conference organizers, conference PC members and reviewer of journals. She has six-year industry working experiences in multiple roles and has strong industry engagements.