[Adapt] Seminar

[黄致格Yvonne]

Hi Adapters,
 
This week, I will give you a talk about evaluation of summarization model. Despite significant progress achieved in text summarization, factual inconsistency in generated summaries still severely limits its practical applications. Among the key factors to ensure factual consistency, a reliable automatic evaluation metric is the first and the most crucial one. However, existing metrics either neglect the intrinsic cause of the factual inconsistency or rely on auxiliary tasks, leading to an unsatisfied correlation with human judgments or increasing the inconvenience of usage in practice.
 
I will introduce a paper from EMNLP 2021 : ‘Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation’. In this paper, the authors proposed a novel metric called CoCo to evaluate the factual consistency in text summarization via counterfactual estimation. 
 
For our online group seminar today, I prepared a Tencent meeting room:
 
Yvonne邀请您参加腾讯会议
 
会议时间：2022/03/09 15:30-18:30 (GMT+08:00) 中国标准时间 - 北京
 
点击链接入会，或添加至会议列表：
 
https://meeting.tencent.com/dm/YUTTJ1SMm5MF
 
#腾讯会议：531-557-282
 
I hope you enjoy my speech even if we don't meet!
 
Time: Wed 4:00pm
 
Venue: Tencent meeting 531-557-282



 
Best Wish,
 
Yvonne Huang
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20220309/0c8f986b/attachment.htm>