Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling
This addresses data scarcity for developers of task-oriented dialog systems, but it is incremental as it builds on existing cross-domain methods.
The paper tackles the problem of data scarcity in cross-domain slot filling for task-oriented dialog systems by proposing a coarse-to-fine approach (Coach) that first detects slot entities and then predicts their types, with a template regularization method to improve adaptation robustness. Experimental results show it significantly outperforms state-of-the-art approaches in slot filling and achieves better adaptation in cross-domain named entity recognition.
As an essential task in task-oriented dialog systems, slot filling requires extensive training data in a certain domain. However, such data are not always available. Hence, cross-domain slot filling has naturally arisen to cope with this data scarcity problem. In this paper, we propose a Coarse-to-fine approach (Coach) for cross-domain slot filling. Our model first learns the general pattern of slot entities by detecting whether the tokens are slot entities or not. It then predicts the specific types for the slot entities. In addition, we propose a template regularization approach to improve the adaptation robustness by regularizing the representation of utterances based on utterance templates. Experimental results show that our model significantly outperforms state-of-the-art approaches in slot filling. Furthermore, our model can also be applied to the cross-domain named entity recognition task, and it achieves better adaptation performance than other existing baselines. The code is available at https://github.com/zliucr/coach.