02/02/2021

Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards

Rahul Aralikatte, Mostafa Abdou, Heather C Lent, Daniel Hershcovich, Anders Søgaard

Keywords:

Abstract Paper Similar Papers

Abstract: Coreference resolution and semantic role labeling are NLP tasks that capture different aspects of semantics, indicating respectively, which expressions refer to the same entity, and what semantic roles expressions serve in the sentence. However, they are often closely interdependent, and both generally necessitate natural language understanding. Do they form a coherent abstract representation of documents? We present a neural network architecture for joint coreference resolution and semantic role labeling for English, and train graph neural networks to model the 'coherence' of the combined shallow semantic graph. Using the resulting coherence score as a reward for our joint semantic analyzer, we use reinforcement learning to encourage global coherence over the document and between semantic annotations. This leads to improvements on both tasks in multiple datasets from different domains, and across a range of encoders of different expressivity, calling, we believe, for a more holistic approach for semantics in NLP.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949171
(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
 5:15 
 0
 0
 0
 0
 9:49 
 0
 0
 0
 0
 14:04 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 11:03 
 0
 0
 0
 0
 12:37 
 0
 0
 0
 0
 7:04 
 0
 0
 0
 0
 10:38 
 0
 0
 0
 0
 10:25 
 0
 0
 0
 0
 16:10 
 0
 0
 0
 0
 15:19 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 4:58 
 0
 0
 0
 0
 6:02 
 0
 0
 0
 0
 15:10 
 0
 0
 0
 0
 9:19 
 0
 0
 0
 0
 14:30 
 0
 0
 0
 0
 4:13 
 0
 0
 0
 0
 6:41 
 0
 0
 0
 0
 3:51 
 0
 0
 0
 0
 14:32 
 0
 0
 0
 0
 10:52 
 0
 0
 0
 0
 14:05 
 0
 0
 0
 0
 8:17 
 0
 0
 0
 0
 6:45 
 0
 0
 0
 0
 12:02 
 0
 0
 0
 0
 14:20 
 0
 0
 0
 0
 9:42 
 0
 0
 0
 0
 10:49 
 0
 0
 0
 0
 10:59 
 0
 0
 0
 0
 6:56 
 0
 0
 0
 0
 10:00 
 0
 0
 0
 0
 11:26 
 0
 0
 0
 0
 12:44 
 0
 0
 0
 0
 10:53 
 0
 0
 0
 0
 15:32 
 0
 0
 0
 0
 18:52 
 0
 0
 0
 0
 12:03 
 0
 0
 0
 0
 10:03 
 0
 0
 0
 0
 19:20