[Adapt] [Seminar] Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

[Yizhu Liu]

Hi Adapters,


I will give a talk about paper  "Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting" which is accepted by ACL 2018.
In this paper, they propose an accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively (i.e., compresses and paraphrases) to generate a concise overall summary. They use a novel sentence-level policy gradient method to bridge the nondifferentiable computation between these two neural networks in a hierarchical way, while maintaining language fluency. Their method achieves the new state-of-theart on all metrics (including human evaluation) on the CNN/Daily Mail dataset, as well as significantly higher abstractiveness scores. Moreover, this model enables parallel decoding of neural generative model that results in substantially faster (10-20x) inference speed as well as 4x faster training convergence than previous long-paragraph encoder-decoder models.


Time: 17:00 Nov 21
Venue: SEIEE 3-517A


Best,
Yizhu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20181121/17911820/attachment.html>