Few Shot Dialogue State Tracking using Meta-learning

01/17/2021
by   Saket Dingliwal, et al.
0

Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information, etc. With the increasing need to deploy such systems in new domains, solving the problem of zero/few-shot DST has become necessary. There has been a rising trend for learning to transfer knowledge from resource-rich domains to unknown domains with minimal need for additional data. In this work, we explore the merits of meta-learning algorithms for this transfer and hence, propose a meta-learner D-REPTILE specific to the DST problem. With extensive experimentation, we provide clear evidence of benefits over conventional approaches across different domains, methods, base models, and datasets with significant (5-25 proposed meta-learner is agnostic of the underlying model and hence any existing state-of-the-art DST system can improve its performance on unknown domains using our training strategy.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/22/2021

Domain Adaptation in Dialogue Systems using Transfer and Meta-Learning

Current generative-based dialogue systems are data-hungry and fail to ad...
05/02/2020

Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking

Zero-shot transfer learning for multi-domain dialogue state tracking can...
02/07/2020

Meta-learning framework with applications to zero-shot time-series forecasting

Can meta-learning discover generic ways of processing time-series (TS) f...
07/10/2020

Meta-Learning Requires Meta-Augmentation

Meta-learning algorithms aim to learn two components: a model that predi...
11/19/2018

Representation based and Attention augmented Meta learning

Deep learning based computer vision fails to work when labeled images ar...
06/02/2019

Sequential Scenario-Specific Meta Learner for Online Recommendation

Cold-start problems are long-standing challenges for practical recommend...
06/12/2020

Learning-to-Learn Personalised Human Activity Recognition Models

Human Activity Recognition (HAR) is the classification of human movement...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.