[Adapt] [Seminar]Keyword-aware Abstractive Summarization by Extracting Set-level Intermediate Summaries
337363896 at qq.com
Tue Nov 3 19:00:08 CST 2020
Tomorrow, I’ll give a talk about my paper ''Keyword-aware Abstractive Summarization by Extracting Set-level Intermediate Summaries'', which is submitted to TheWebConference (WWW).
In this paper, we propose a extractor-abstractor framework in which the keyword-based extractor selects a few sets of salient sentences from the input document and then the abstractor paraphrases these sets of sentences in parallel, which are more aligned to the summary, to generate the final summary. The new extractor and abstractor are pre-trained from a set of “pseudo summaries” , and then further trained together in a reinforcement learning framework. The results show that the proposed model generates high-quality summaries with faster training speed and less training memory footprint, and outperforms the state-of-the-art models.
Time: Wed 4:00pm
Venue: SEIEE 3-414
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Adapt