SIM: A Slot-Independent Neural Model for Dialogue State Tracking

TL;DR

This paper introduces SIM, a slot-independent neural model for dialogue state tracking that maintains constant complexity regardless of slot quantity, achieving state-of-the-art results with reduced model size.

Contribution

The paper proposes a novel slot-independent neural model that reduces complexity and size while improving performance in dialogue state tracking.

Findings

Achieves state-of-the-art results on WoZ and DSTC2 datasets.

Uses attention mechanisms between user utterance and system actions.

Model size is only 20% of previous models.

Abstract

Dialogue state tracking is an important component in task-oriented dialogue systems to identify users' goals and requests as a dialogue proceeds. However, as most previous models are dependent on dialogue slots, the model complexity soars when the number of slots increases. In this paper, we put forward a slot-independent neural model (SIM) to track dialogue states while keeping the model complexity invariant to the number of dialogue slots. The model utilizes attention mechanisms between user utterance and system actions. SIM achieves state-of-the-art results on WoZ and DSTC2 tasks, with only 20% of the model size of previous models.