19/10/2020

Ranking clarification questions via natural language inference

Vaibhav Kumar, Vikas Raunak, Jamie Callan

Keywords: natural language inference, bert, clarification question

Abstract Paper Similar Papers

Abstract: Given a natural language query, teaching machines to ask clarifying questions is of immense utility in practical natural language processing systems. Such interactions could help in filling information gaps for better machine comprehension of the query. For the task of ranking clarification questions, we hypothesize that determining whether a clarification question pertains to a missing entry in a given post (on QA forums such as StackExchange) could be considered as a special case of Natural Language Inference (NLI), where both the post and the most relevant clarification question point to a shared latent piece of information or context. We validate this hypothesis by incorporating representations from a Siamese BERT model fine-tuned on NLI and Multi-NLI datasets into our models and demonstrate that our best performing model obtains a relative performance improvement of 40 percent and 60 percent respectively (on the key metric of Precision@1), over the state-of-the-art baseline(s) on the two evaluation sets of the StackExchange dataset, thereby, significantly surpassing the state-of-the-art.

The video of this talk cannot be embedded. You can watch it here:
https://dl.acm.org/doi/10.1145/3340531.3412137#sec-supp
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at CIKM 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
 4:55 
 0
 0
 0
 0
 12:16 
 0
 0
 0
 0
 9:45 
 0
 0
 0
 0
 7:55 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 4:58 
 0
 0
 0
 0
 14:16 
 0
 0
 0
 0
 15:01 
 0
 0
 0
 0
 11:50 
 0
 0
 0
 0
 14:52 
 0
 0
 0
 0
 5:21 
 0
 0
 0
 0
 12:42 
 0
 0
 0
 0
 12:07 
 0
 0
 0
 0
 9:46 
 0
 0
 0
 0
 17:52 
 0
 0
 0
 0
 6:54 
 0
 0
 0
 0
 11:43 
 0
 0
 0
 0
 15:01 
 0
 0
 0
 0
 14:06 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 7:10 
 0
 0
 0
 0
 11:47 
 0
 0
 0
 0
 6:53 
 0
 0
 0
 0
 6:38 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 14:03 
 0
 0
 0
 0
 12:35 
 0
 0
 0
 0
 6:50 
 0
 0
 0
 0
 14:09 
 0
 0
 0
 0
 17:06 
 0
 0
 0
 0
 4:44 
 0
 0
 0
 0
 6:02 
 0
 0
 0
 0
 11:03 
 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 10:13 
 0
 0
 0
 0
 18:24 
 0
 0
 0
 0
 14:58 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 12:11 
 0
 0
 0
 0
 9:29