25/07/2020

Distilling knowledge for fast retrieval-based chat-bots

Amir Vakili Tahami, Kamyar Ghajar, Azadeh Shakery

Keywords: retrieval-based chat-bot, response ranking, neural information retrieval

Abstract Paper Similar Papers

Abstract: Response retrieval is a subset of neural ranking in which a model selects a suitable response from a set of candidates given a conversation history. Retrieval-based chat-bots are typically employed in information seeking conversational systems such as customer support agents. To make pairwise comparisons between a conversation history and a candidate response, two approaches are common: cross-encoders performing full self-attention over the pair and bi-encoders encoding the pair separately. The former gives better prediction quality but is too slow for practical use. In this paper, we propose a new cross-encoder architecture and transfer knowledge from this model to a bi-encoder model using distillation. This effectively boosts bi-encoder performance at no cost during inference time. We perform a detailed analysis of this approach on three response retrieval datasets.

The video of this talk cannot be embedded. You can watch it here:
https://dl.acm.org/doi/10.1145/3397271.3401296#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 SIGIR 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
 10:34 
 0
 0
 0
 0
 15:47 
 0
 0
 0
 0
 13:50 
 0
 0
 0
 0
 21:30 
 0
 0
 0
 0
 12:02 
 0
 0
 0
 1
 11:06 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 12:19 
 0
 0
 0
 0
 15:12 
 0
 0
 0
 0
 7:04 
 0
 0
 0
 0
 2:55 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 5:08 
 0
 0
 0
 1
 10:01 
 0
 0
 0
 0
 4:27 
 0
 0
 0
 0
 8:33 
 0
 0
 0
 0
 8:42 
 0
 0
 0
 0
 4:44 
 0
 0
 0
 0
 14:49 
 0
 0
 0
 0
 5:26 
 0
 0
 0
 0
 5:05 
 0
 0
 0
 0
 13:33 
 0
 0
 0
 0
 12:39 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 18:52 
 0
 0
 0
 0
 6:58 
 0
 0
 0
 0
 6:09 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 11:21 
 0
 0
 0
 0
 21:04 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 19:27 
 0
 0
 0
 0
 15:41 
 0
 0
 0
 0
 11:43 
 0
 0
 0
 0
 15:12 
 0
 0
 0
 0
 13:47 
 0
 0
 0
 0
 14:43 
 0
 0
 0
 0
 7:18