[Adapt] [Seminar] Visually Grounded Reasoning across Languages and Cultures

[hongru]

Hi Adapters,

In this seminar, I would talk about a multimodal reasoning dataset paper: Visually Grounded Reasoning across Languages and Cultures, which is nominated as the best long paper of EMNLP 2021. 
I would try my best to tell you why they intend to create such a dataset and how they create it. Hope you enjoy it and discuss why it can be nominated as BP. 😊

Best,
Hongru

从 Windows 版邮件发送

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20211102/f2093a10/attachment.htm>