Efficient Dialogue State Tracking by Selectively Overwriting Memory

TL;DR

This paper introduces SOM-DST, a novel dialogue state tracking method that uses a selective overwriting mechanism to improve efficiency and accuracy in open vocabulary settings, outperforming previous models.

Contribution

It proposes a new selective overwriting mechanism for dialogue state tracking that decomposes the task and enhances training effectiveness and performance.

Findings

Achieves state-of-the-art joint goal accuracy on MultiWOZ datasets.

Reduces decoder burden by focusing on specific sub-tasks.

Analyzes accuracy gaps to suggest future improvements.

Abstract

Recent works in dialogue state tracking (DST) focus on an open vocabulary-based setting to resolve scalability and generalization issues of the predefined ontology-based approaches. However, they are inefficient in that they predict the dialogue state at every turn from scratch. Here, we consider dialogue state as an explicit fixed-sized memory and propose a selectively overwriting mechanism for more efficient DST. This mechanism consists of two steps: (1) predicting state operation on each of the memory slots, and (2) overwriting the memory with new values, of which only a few are generated according to the predicted state operations. Our method decomposes DST into two sub-tasks and guides the decoder to focus only on one of the tasks, thus reducing the burden of the decoder. This enhances the effectiveness of training and DST performance. Our SOM-DST (Selectively Overwriting Memory for Dialogue State Tracking) model achieves state-of-the-art joint goal accuracy with 51.72% in MultiWOZ 2.0 and 53.01% in MultiWOZ 2.1 in an open vocabulary-based DST setting. In addition, we analyze the accuracy gaps between the current and the ground truth-given situations and suggest that it is a promising direction to improve state operation prediction to boost the DST performance.