Learning to Learn End-to-End Goal-Oriented Dialog From Related Dialog Tasks

TL;DR

This paper introduces a meta-learning approach that effectively leverages related dialog data to improve end-to-end goal-oriented dialog systems, reducing data collection costs and enhancing performance.

Contribution

It proposes a novel meta-learning method for selectively utilizing related dialog data, addressing inconsistency issues and boosting accuracy in target tasks.

Findings

Significant accuracy improvements in dialog tasks

Effective use of limited target data with related data

Meta-learning approach outperforms naive methods

Abstract

For each goal-oriented dialog task of interest, large amounts of data need to be collected for end-to-end learning of a neural dialog system. Collecting that data is a costly and time-consuming process. Instead, we show that we can use only a small amount of data, supplemented with data from a related dialog task. Naively learning from related data fails to improve performance as the related data can be inconsistent with the target task. We describe a meta-learning based method that selectively learns from the related dialog task data. Our approach leads to significant accuracy improvements in an example dialog task.