Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking

TL;DR

This paper introduces DiCoS-DST, a dynamic dialogue content selection method for dialogue state tracking that improves performance by selecting relevant history for each slot, outperforming existing models.

Contribution

It proposes a novel approach to dynamically select relevant dialogue history for each slot, addressing the limitations of using consistent history throughout the process.

Findings

Achieves state-of-the-art results on MultiWOZ 2.1 and 2.2 datasets.

Outperforms baseline models on multiple benchmark datasets.

Effectively reduces distracting information in dialogue state tracking.

Abstract

In dialogue state tracking, dialogue history is a crucial material, and its utilization varies between different models. However, no matter how the dialogue history is used, each existing model uses its own consistent dialogue history during the entire state tracking process, regardless of which slot is updated. Apparently, it requires different dialogue history to update different slots in different turns. Therefore, using consistent dialogue contents may lead to insufficient or redundant information for different slots, which affects the overall performance. To address this problem, we devise DiCoS-DST to dynamically select the relevant dialogue contents corresponding to each slot for state updating. Specifically, it first retrieves turn-level utterances of dialogue history and evaluates their relevance to the slot from a combination of three perspectives: (1) its explicit connection to the slot name; (2) its relevance to the current turn dialogue; (3) Implicit Mention Oriented Reasoning. Then these perspectives are combined to yield a decision, and only the selected dialogue contents are fed into State Generator, which explicitly minimizes the distracting information passed to the downstream state prediction. Experimental results show that our approach achieves new state-of-the-art performance on MultiWOZ 2.1 and MultiWOZ 2.2, and achieves superior performance on multiple mainstream benchmark datasets (including Sim-M, Sim-R, and DSTC2).