[Adapt] [Seminar]Heterogeneous Graph Neural Networks for Extractive Document Summarization

Yizhu Liu 337363896 at qq.com
Wed Apr 28 10:28:08 CST 2021


Hi Adapters,

Today, I’ll give a talk about paper ''Heterogeneous Graph Neural Networks for Extractive Document Summarization'', which is accepted by ACL 2020.

In this paper, they present a heterogeneous graph-based neural network for extractive summarization (HETERSUMGRAPH), which contains semantic nodes of different granularity levels apart from sentences. These additional nodes act as the intermediary between sentences and enrich the cross-sentence relations. Besides, the graph structure is flexible in natural extension from a single-document setting to multi-document via introducing document nodes.

Time: Wed 4:00pm

Venue: SEIEE 3-414

Best,
Yizhu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20210428/55b09dda/attachment.html>


More information about the Adapt mailing list