02/02/2021

Contextualized Rewriting for Text Summarization

Guangsheng Bao, Yue Zhang

Keywords:

Abstract Paper Similar Papers

Abstract: Extractive summarization suffers from irrelevance, redundancy and incoherence. Existing work shows that abstractive rewriting for extractive summaries can improve the conciseness and readability. These rewriting systems consider extracted summaries as the only input, which is relatively focused but can lose important background knowledge. In this paper, we investigate contextualized rewriting, which ingests the entire original document. We formalize contextualized rewriting as a seq2seq problem with group alignments, introducing group tag as a solution to model the alignments, identifying extracted summaries through content-based addressing. Results show that our approach significantly outperforms non-contextualized rewriting systems without requiring reinforcement learning, achieving strong improvements on ROUGE scores upon multiple extractive summarizers.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949208
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 12:01 
 0
 0
 0
 0
 12:24 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 15:16 
 0
 0
 0
 0
 11:30 
 0
 0
 1
 1
 4:58 
 0
 0
 0
 0
 7:33 
 0
 0
 0
 0
 7:18 
 0
 0
 0
 0
 6:32 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 6:58 
 0
 0
 0
 0
 15:58 
 0
 0
 0
 0
 17:48 
 0
 0
 0
 0
 19:21 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 15:27 
 0
 0
 0
 0
 4:38 
 0
 0
 0
 0
 11:26 
 0
 0
 0
 0
 6:41 
 0
 0
 0
 0
 12:11 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 12:04 
 0
 0
 0
 0
 7:08 
 0
 0
 0
 0
 15:20 
 0
 0
 0
 0
 11:48 
 0
 0
 0
 0
 10:03 
 0
 0
 0
 0
 11:36 
 0
 0
 0
 0
 11:46 
 0
 0
 0
 0
 10:02 
 0
 0
 0
 0
 14:27 
 0
 0
 0
 0
 10:14 
 0
 0
 0
 0
 14:02 
 0
 0
 0
 0
 6:54 
 0
 0
 0
 0
 11:05 
 0
 0
 0
 0
 7:05 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 17:39 
 0
 0
 0
 0
 11:16 
 0
 0
 0
 0
 24:38 
 0
 0
 0
 0
 5:00