[Adapt] [Seminar] Graph-based Document Summarization

[Qiqi Wang]

Hi all,

Currently, NLP models widely encode text/document by sequence to extract
contextual information. The BERT, Roberta, et al. neural networks-based
models represent this idea. However, sentences or paragraphs in a document
may have contextual relations and are related to distance sentences or
paragraphs. In the summarization task, distance information may be
necessary for the summary. Therefore, in this seminar, I will introduce a
graph-based document representation and two papers which use the idea.

*Time:* 2022/04/06 16:00-18:00

*Venus: *
Tecent Meeting Link: https://meeting.tencent.com/dm/qDcCYYV2YUIj
Tecent Meeting Number：202-706-320

Hope you will enjoy this topic. Have a nice day.

Best regards,
Qiqi
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20220406/7b0f21fb/attachment.htm>