[Adapt] [Seminar]Entity Commonsense Representation for Neural Abstractive Summarization

Yizhu Liu 337363896 at qq.com
Tue Oct 15 21:41:17 CST 2019


Hi Adapters,


I will give a talk about paper  "  Entity Commonsense Representation for Neural Abstractive Summarization " which is accepted by naacl 2018.


In this paper, they use an off-the-shelf entity linking system (ELS) to extract linked entities and propose Entity2Topic (E2T), a module easily attachable to a sequence-to-sequence model that transforms a list of entities into a vector representation of the topic of the summary. 
By applying E2T to a simple sequenceto-sequence model with attention mechanism as base model, we see significant improvements of the performance in the Gigaword (sentence to title) and CNN (long document to multi-sentence highlights) summarization datasets by at least 2 ROUGE points. 


Time: 16:30 October 15
Venue: SEIEE 3-414


Best,
Yizhu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20191015/0d46d620/attachment.html>


More information about the Adapt mailing list