Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking

TL;DR

This paper introduces a Hierarchical Dynamic Copy Network that improves dialogue state tracking by focusing on the most informative dialogue turns, enhancing slot value extraction in task-oriented dialogue systems.

Contribution

It proposes a hierarchical attention mechanism with a focus loss to better identify key dialogue turns for improved state tracking.

Findings

Achieves 46.76% joint accuracy on MultiWOZ 2.1 dataset.

Effectively focuses on informative turns, improving slot value extraction.

Outperforms existing models in dialogue state tracking accuracy.

Abstract

Recently, researchers have explored using the encoder-decoder framework to tackle dialogue state tracking (DST), which is a key component of task-oriented dialogue systems. However, they regard a multi-turn dialogue as a flat sequence, failing to focus on useful information when the sequence is long. In this paper, we propose a Hierarchical Dynamic Copy Network (HDCN) to facilitate focusing on the most informative turn, making it easier to extract slot values from the dialogue context. Based on the encoder-decoder framework, we adopt a hierarchical copy approach that calculates two levels of attention at the word- and turn-level, which are then renormalized to obtain the final copy distribution. A focus loss term is employed to encourage the model to assign the highest turn-level attention weight to the most informative turn. Experimental results show that our model achieves 46.76% joint accuracy on the MultiWOZ 2.1 dataset.