Out-of-Task Training for Dialog State Tracking Models

TL;DR

This paper introduces a novel approach to improve dialog state tracking by leveraging non-dialog NLP data, addressing data sparsity issues and enhancing model training.

Contribution

It demonstrates the effective use of unrelated NLP data for training dialog state trackers, expanding beyond traditional dialog-specific datasets.

Findings

Non-dialog NLP data improves DST performance.

Transfer learning mitigates data sparsity in dialog tasks.

Method enhances generalization of DST models.

Abstract

Dialog state tracking (DST) suffers from severe data sparsity. While many natural language processing (NLP) tasks benefit from transfer learning and multi-task learning, in dialog these methods are limited by the amount of available data and by the specificity of dialog applications. In this work, we successfully utilize non-dialog data from unrelated NLP tasks to train dialog state trackers. This opens the door to the abundance of unrelated NLP corpora to mitigate the data sparsity issue inherent to DST.