02/02/2021

Unsupervised Opinion Summarization with Content Planning

Reinald Kim Amplayo, Stefanos Angelidis, Mirella Lapata

Keywords:

Abstract Paper Similar Papers

Abstract: The recent success of deep learning techniques for abstractive summarization is predicated on the availability of large-scale datasets. When summarizing reviews (e.g., for products or movies), such training data is neither available nor can be easily sourced, motivating the development of methods which rely on synthetic datasets for supervised training. We show that explicitly incorporating content planning in a summarization model not only yields output of higher quality, but also allows the creation of synthetic datasets which are more natural, resembling real world document-summary pairs. Our content plans take the form of aspect and sentiment distributions which we induce from data without access to expensive annotations. Synthetic datasets are created by sampling pseudo-reviews from a Dirichlet distribution parametrized by our content planner, while our model generates summaries based on input reviews and induced content plans. Experimental results on three domains show that our approach outperforms competitive models in generating informative, coherent, and fluent summaries that capture opinion consensus.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949303
(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
 10:55 
 0
 0
 0
 0
 6:37 
 0
 0
 0
 0
 7:39 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 6:14 
 0
 0
 0
 0
 7:00 
 0
 0
 0
 0
 14:40 
 0
 0
 0
 0
 10:53 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 4:43 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 9:15 
 0
 0
 0
 0
 5:22 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 14:51 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 13:50 
 0
 0
 0
 0
 4:49 
 0
 0
 0
 0
 3:08 
 0
 0
 0
 0
 19:21 
 0
 0
 0
 0
 14:22 
 0
 0
 0
 0
 10:49 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 12:03 
 0
 0
 0
 1
 5:49 
 0
 0
 0
 0
 1:03 
 0
 0
 0
 0
 4:00 
 0
 0
 0
 1
 3:14 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 8:54 
 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 14:09 
 0
 0
 0
 0
 5:43 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 3:52 
 0
 0
 0
 0
 12:32