Schema Encoding for Transferable Dialogue State Tracking

TL;DR

This paper introduces SETDST, a neural dialogue state tracking method that leverages schema encoding to enable effective transfer to new domains with minimal data, improving accuracy on multi-domain benchmarks.

Contribution

The paper proposes a novel schema encoding approach that enhances transferability of dialogue state tracking models across domains, reducing the need for extensive domain-specific training data.

Findings

SETDST improves joint accuracy by 1.46 points on MultiWOZ 2.1.

Schema encoding enables effective transfer to new domains.

The method reduces data requirements for multi-domain dialogue systems.

Abstract

Dialogue state tracking (DST) is an essential sub-task for task-oriented dialogue systems. Recent work has focused on deep neural models for DST. However, the neural models require a large dataset for training. Furthermore, applying them to another domain needs a new dataset because the neural models are generally trained to imitate the given dataset. In this paper, we propose Schema Encoding for Transferable Dialogue State Tracking (SETDST), which is a neural DST method for effective transfer to new domains. Transferable DST could assist developments of dialogue systems even with few dataset on target domains. We use a schema encoder not just to imitate the dataset but to comprehend the schema of the dataset. We aim to transfer the model to new domains by encoding new schemas and using them for DST on multi-domain settings. As a result, SET-DST improved the joint accuracy by 1.46 points on MultiWOZ 2.1.