//
微软亚洲研究院 ACE Talk 系列讲座旨在邀请杰出的学术新星分享科研成果，为学生与研究员提供相互交流学习与洞悉前沿动态的平台。
第二十期 ACE Talk，我们特别邀请到来自滑铁卢大学的助理教授 Haoyue Shi 为我们带来以“Learning language structures through grounding and beyond”为主题的报告，介绍一种新的学习语言结构的方法，该方法通过从其他模态和语言获取远程监督，以及一种无需目标语言人类注释即可实现跨语言模型转移的技术。
讲座信息
时间：7 月 4 日（周四）9:00 - 10:30
地点：线上
日程：
• 嘉宾报告（9:00 - 10:00）
• Q&A（10:00-10:30）
报名方式
欢迎扫描下方二维码填写报名问卷，报名成功后将收到邮件通知，邮件中将提供讲座 Teams 线上会议链接。
报名截止时间：7 月 3 日（周三）下午 2:00
报名链接：https://jinshuju.net/f/JJGnfn
嘉宾介绍
Haoyue Shi
滑铁卢大学
助理教授
Freda Shi, a.k.a. Haoyue Shi, is an Assistant Professor in the David R. Cheriton School of Computer Science at the University of Waterloo, where she directs the Computation, Language, Intelligence, and Grounding (CompLING) Laboratory. Shi received her Ph.D. in Computer Science from the Toyota Technological Institute at Chicago, and her B.S. in Intelligence Science from Peking University. Her work has been recognized by a thesis of distinction award from TTIC, Best Paper Nominations at ACL 2019 and 2021, a Google Ph.D. fellowship, and a finalist award for the Facebook fellowship.
报告简介
Learning language structures through grounding and beyond
In the first part of the talk, I will present my PhD dissertation, Learning Language Structures through Grounding, where I discuss and advocate for the potential of the family of tasks that aim to learn language structures through distant supervision from other modalities and other languages. I will start by introducing the task of visually grounded grammar induction and our proposed solution based on visual concreteness estimation. Second, I will describe our work on learning semantic structures of sentences (i.e., their corresponding programs) by grounding program implementations to their execution outcomes. Towards language-universal NLP, I will describe our work that efficiently transfers models from one language to another without any human annotations in the target language, using cross-lingual word correspondence as grounding signals.
Finally, I will conclude by sharing a few future directions we are interested in pursuing at the CompLING lab.
主持人简介
黄羽盼
微软亚洲研究院
高级研究员
Yupan Huang is currently a Sr Researcher at Microsoft Research Asia-Pacific Vancouver. She obtained her Ph.D. degree in Computer Science from Sun Yat-sen University in 2023 as a member of the joint Ph.D. program between Sun Yat-sen University and Microsoft Research Asia. She also visited the University of Cambridge in 2023. Her research interests focus on multimodal AI. She has contributed to the innovation of multimodal foundation models, generative AI techniques, and document intelligence.
关于ACE Talk
ACE (Accelerate, Create, Empower) Talk Series epitomizes our commitment across three dimensions. To accelerate the swift adoption of cutting-edge research where researchers and students can share the latest breakthroughs and advancements. To create an environment that nurtures novel ideas and fosters the genesis of innovative solutions to complex problems. At its core, we are dedicated to empowering individuals, including our speakers and audiences to drive positive changes on a broader scale. Through this endeavor, we aspire to enhance global communication and cultivate a diverse academic atmosphere, connecting talented individuals worldwide and ultimately contributing to meaningful change within the academic research community
