# Time Masking: Leveraging Temporal Information in Spoken Dialogue Systems

## TL;DR

This paper introduces a novel time mask method that uses wall-clock time differences to improve dialogue state tracking in spoken dialogue systems, outperforming previous distance-based approaches.

## Contribution

The paper proposes a new time mask technique leveraging wall-clock time differences, enhancing dialogue state tracking accuracy over existing offset-based methods.

## Key findings

- Outperforms existing distance offset methods on benchmark datasets
- Effective in capturing finer-grained temporal information
- Improves dialogue state tracking accuracy

## Abstract

In a spoken dialogue system, dialogue state tracker (DST) components track the state of the conversation by updating a distribution of values associated with each of the slots being tracked for the current user turn, using the interactions until then. Much of the previous work has relied on modeling the natural order of the conversation, using distance based offsets as an approximation of time. In this work, we hypothesize that leveraging the wall-clock temporal difference between turns is crucial for finer-grained control of dialogue scenarios. We develop a novel approach that applies a {\it time mask}, based on the wall-clock time difference, to the associated slot embeddings and empirically demonstrate that our proposed approach outperforms existing approaches that leverage distance offsets, on both an internal benchmark dataset as well as DSTC2.