08/12/2020

Generalized Shortest-Paths Encoders for AMR-to-Text Generation

Lisa Jin, Daniel Gildea

Keywords:

Abstract Paper Similar Papers

Abstract: For text generation from semantic graphs, past neural models encoded input structure via gated convolutions along graph edges. Although these operations provide local context, the distance messages can travel is bounded by the number of encoder propagation steps. We adopt recent efforts of applying Transformer self-attention to graphs to allow global feature propagation. Instead of feeding shortest paths to the vertex self-attention module, we train a model to learn them using generalized shortest-paths algorithms. This approach widens the receptive field of a graph encoder by exposing it to all possible graph paths. We explore how this path diversity affects performance across levels of AMR connectivity, demonstrating gains on AMRs of higher reentrancy counts and diameters. Analysis of generated sentences also supports high semantic coherence of our models for reentrant AMRs. Our best model achieves a 1.4 BLEU and 1.8 chrF++ margin over a baseline that encodes only pairwise-unique shortest paths.

The video of this talk cannot be embedded. You can watch it here:
https://underline.io/lecture/6261-generalized-shortest-paths-encoders-for-amr-to-text-generation
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at COLING 2020 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
 13:14 
 0
 0
 0
 0
 10:56 
 0
 0
 0
 0
 10:40 
 0
 0
 0
 0
 7:43 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 11:35 
 0
 0
 0
 1
 10:44 
 0
 0
 0
 0
 5:39 
 0
 0
 0
 0
 9:39 
 0
 0
 0
 0
 13:43 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 14:36 
 0
 0
 0
 0
 12:05 
 0
 0
 0
 0
 5:03 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 6:04 
 0
 0
 0
 0
 14:53 
 0
 0
 0
 0
 15:25 
 0
 0
 0
 0
 3:10 
 0
 0
 0
 0
 8:49 
 0
 0
 0
 0
 13:53 
 0
 0
 0
 0
 11:22 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 17:39 
 0
 0
 0
 0
 3:38 
 0
 0
 0
 0
 12:13 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 2:50 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 13:35 
 0
 0
 0
 0
 14:41 
 0
 0
 0
 0
 4:09 
 0
 0
 0
 0
 3:47 
 0
 0
 0
 0
 3:05 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 11:12 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 16:46