02/02/2021

Copy That! Editing Sequences by Copying Spans

Sheena Panthaplackel, Miltiadis Allamanis, Marc Brockschmidt

Keywords:

Abstract Paper Similar Papers

Abstract: Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code. In this paper, we argue that common seq2seq models (with a facility to copy single tokens) are not a natural fit for such tasks, as they have to explicitly copy each unchanged token. We present an extension of seq2seq models capable of copying entire spans of the input to the output in one step, greatly reducing the number of decisions required during inference. This extension means that there are now many ways of generating the same output, which we handle by deriving a new objective for training and a variation of beam search for inference that explicitly handles this problem. In our experiments on a range of editing tasks of natural language and source code, we show that our new model consistently outperforms simpler baselines.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38947904
(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
 9:31 
 0
 0
 0
 0
 14:27 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 12:20 
 0
 0
 0
 0
 5:58 
 0
 0
 0
 0
 6:52 
 0
 0
 0
 0
 18:48 
 0
 0
 0
 0
 17:06 
 0
 0
 0
 0
 5:59 
 0
 0
 0
 0
 10:09 
 0
 0
 0
 0
 6:48 
 0
 0
 0
 0
 5:22 
 0
 0
 0
 0
 11:36 
 0
 0
 0
 0
 6:14 
 0
 0
 0
 0
 11:27 
 0
 0
 0
 0
 15:08 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 14:33 
 0
 0
 0
 0
 9:58 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 0:59 
 0
 0
 0
 1
 4:54 
 0
 0
 0
 0
 6:14 
 0
 0
 0
 0
 4:55 
 0
 0
 0
 0
 14:02 
 0
 0
 0
 0
 11:37 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 15:59 
 0
 0
 0
 0
 5:02 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 6:51 
 0
 0
 0
 0
 12:32 
 0
 0
 0
 0
 11:49 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 10:51 
 0
 0
 0
 0
 13:48 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 5:16