Global-Locally Self-Attentive Dialogue State Tracker
This improves task-oriented dialogue systems by enhancing tracking of rare states, though it is incremental as it builds on existing self-attention methods.
The paper tackles dialogue state tracking by proposing GLAD, a model that uses global-local self-attention to share parameters and learn slot-specific features, achieving state-of-the-art performance with 88.1% joint goal accuracy and 97.1% request accuracy on WoZ, and 74.5% joint goal accuracy and 97.5% request accuracy on DSTC2.
Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules. Our model uses global modules to share parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features. We show that this significantly improves tracking of rare states and achieves state-of-the-art performance on the WoZ and DSTC2 state tracking tasks. GLAD obtains 88.1% joint goal accuracy and 97.1% request accuracy on WoZ, outperforming prior work by 3.7% and 5.5%. On DSTC2, our model obtains 74.5% joint goal accuracy and 97.5% request accuracy, outperforming prior work by 1.1% and 1.0%.