[Adapt] [Seminar] An Entity-Driven Framework for Abstractive Summarization

[Yizhu Liu]

Hi Adapters,


I will give a talk about paper  " An Entity-Driven Framework for Abstractive Summarization" which is accepted by emnlp 2019.


In this paper, they introduce SENECA, a novel System for ENtitydrivEn Coherent Abstractive summarization framework that leverages entity information to generate informative and coherent abstracts.


Their framework takes a two-step approach:(1) an entity-aware content selection module first identifies salient sentences from the input, then (2) an abstract generation module conducts cross-sentence information compression and abstraction to generate the final summary, which is trained with rewards to promote coherence, conciseness, and clarity. The two components are further connected using reinforcement learning. 

Automatic evaluation shows that the model significantly outperforms previous state-of-the-art on ROUGE and the proposed coherence measures on New York Times and CNN/Daily Mail datasets. Human judges further rate our system summaries as more informative and coherent than those by popular summarization models.

Time: 16:30 September 25
Venue: SEIEE 3-414


Best,
Yizhu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20190924/8862067f/attachment.html>