arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.11727cs.CL
收藏

Coach:一种由粗到精的跨域槽填充方法

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling

Center for Artificial Intelligence Research (CAiRE)(人工智能研究中心(CAiRE));The Hong Kong University of Science and Technology(香港科技大学)

Zihan Liu, Genta Indra Winata, Peng Xu, Pascale Fung

摘要:

作为面向任务的对话系统中的一项基本任务,槽填充需要一定领域的大量训练数据。然而,并不总是有这种数据。因此,跨域插槽填充自然出现,以应对这种数据稀缺问题。在本文中,我们提出了一个粗到精的方法(教练)跨域槽填充。我们的模型首先通过检测令牌是否是插槽实体来学习插槽实体的一般模式。然后预测插槽实体的特定类型。此外,我们提出了一个模板正则化的方法,以提高自适应鲁棒性的话语模板的基础上,通过正则化的表示。实验结果表明,我们的模型显着优于国家的最先进的方法在槽填充。此外,我们的模型也可以应用到跨域的命名实体识别任务,它实现了更好的适应性能比其他现有的基线。该代码可在https://github.com/zliucr/coach上获得。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑