SIM: A Slot-Independent Neural Model for Dialogue State Tracking
This addresses the issue of high model complexity in task-oriented dialogue systems, which is incremental as it builds on existing methods but introduces a novel slot-independent approach.
The paper tackles the problem of model complexity scaling with the number of dialogue slots in dialogue state tracking by proposing a slot-independent neural model (SIM) that uses attention mechanisms, achieving state-of-the-art results on WoZ and DSTC2 tasks with only 20% of the model size of previous models.
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.