[Adapt] [Seminar] Multimodal Logical Inference System for Visual-Textual Entailment

[Kenny Zhu]

The venue is 03-414, not 04-414. Please take note.

 

Kenny

 

From: adapt-bounces at cs.sjtu.edu.cn [mailto:adapt-bounces at cs.sjtu.edu.cn] On Behalf Of hongru
Sent: Wednesday, September 18, 2019 10:52 AM
To: adapt at cs.sjtu.edu.cn
Subject: [Adapt] [Seminar] Multimodal Logical Inference System for Visual-Textual Entailment

 

Hi Adapters,

 

In this seminar, I’ll introduce the paper “Multimodal Logical Inference System for Visual-Textual Entailment (ACL 2019)”, which presents an unsupervised inference system that can effectively prove entailment relations between image and textual data. Unlike other popular NN-based model, the solving procedure of this system is interpretable, which may give us another point of view of solving inference problem.

 

Time: Wed 4:30pm

Venue: SEIEE 4-414

 

Best regards,

Hongru

 

发送自 Windows 10 版 <https://go.microsoft.com/fwlink/?LinkId=550986> 邮件应用

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20190918/711e852f/attachment.html>