02/02/2021

A Student-Teacher Architecture for Dialog Domain Adaptation Under the Meta-Learning Setting

Kun Qian, Wei Wei, Zhou Yu

Keywords:

Abstract Paper Similar Papers

Abstract: Numerous new dialog domains are being created every day while collecting data for these domains is extremely costly since it involves human interactions. Therefore, it is essential to develop algorithms that can adapt to different domains efficiently when building data-driven dialog models. Most recent research on domain adaption focuses on giving the model a better initialization, rather than optimizing the adaptation process. We propose an efficient domain adaptive task-oriented dialog system model, which incorporates a meta-teacher model to emphasize the different impacts between generated tokens with respect to the context. We first train our base dialog model and meta-teacher model adversarially in a meta-learning setting on rich-resource domains. The meta-teacher learns to quantify the importance of tokens under different contexts across different domains. During adaptation, the meta-teacher guides the dialog model to focus on important tokens in order to achieve better adaptation efficiency. We evaluate our model on two multi-domain datasets, MultiWOZ and Google Schema-Guided Dialogue, and achieve state-of-the-art performance.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948380
(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
 11:58 
 0
 0
 0
 0
 12:53 
 0
 0
 0
 0
 5:06 
 1
 1
 0
 0
 5:13 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 15:32 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 11:11 
 0
 0
 0
 0
 9:27 
 1
 1
 0
 0
 3:28 
 0
 0
 0
 0
 10:10 
 0
 0
 0
 0
 7:09 
 0
 0
 0
 0
 15:42 
 0
 0
 0
 0
 14:20 
 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 2:45 
 0
 0
 0
 0
 7:41 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 4:42 
 0
 0
 0
 0
 13:41 
 0
 0
 0
 0
 14:58 
 0
 0
 0
 0
 10:19 
 0
 0
 0
 0
 15:57 
 0
 0
 0
 0
 15:28 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 0:59 
 0
 0
 0
 0
 9:58 
 0
 0
 0
 0
 7:25 
 0
 0
 0
 0
 16:09 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 10:15 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 17:11 
 0
 0
 0
 0
 2:56 
 0
 0
 0
 0
 3:55 
 0
 0
 0
 0
 17:05 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 6:40 
 0
 0
 0
 0
 9:15