论文标题
教练：跨域插槽填充的粗到精细方法
Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling
论文作者
论文摘要
作为面向任务的对话系统的重要任务，插槽填充需要在某个域中进行大量的培训数据。但是，此类数据并不总是可用。因此，跨域插槽填充自然会解决这些数据稀缺问题。在本文中，我们提出了一种跨域插槽填充的粗到精细方法（教练）。我们的模型首先通过检测令牌是否是插槽实体来了解插槽实体的一般模式。然后，它可以预测插槽实体的特定类型。此外，我们提出了一种模板正规化方法，通过根据语音模板定期表示话语来改善适应性鲁棒性。实验结果表明，我们的模型在插槽填充中的表现明显优于最先进的方法。此外，我们的模型也可以应用于名为“实体识别任务”的跨域，并且比其他现有基线获得了更好的适应性性能。该代码可在https://github.com/zliucr/coach上找到。
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.
