Out-of-domain Detection for Natural Language Understanding in Dialog Systems

09/09/2019 ∙ by Yinhe Zheng, et al. ∙ 13

In natural language understanding components, detecting out-of-domain (OOD) inputs is important for dialogue systems since wrongly accepting these OOD utterances that are not currently supported may lead to catastrophic failures of the entire system. Entropy regularization is an effective solution to avoid such failures, however, its computation heavily depends on OOD data, which are expensive to collect. In this paper, we propose a novel text generation model to produce high-quality OOD samples and thereby improve the performance of OOD detection. The proposed model can also utilize a set of unlabeled data to improve the effectiveness of these generated OOD samples. Experiments show that our method can effectively improve the OOD detection performance of a NLU module.



There are no comments yet.


page 1

page 2

page 3

page 4

Code Repositories


An implementation of the Pseudo OOD Generation model (POG), detailed in arxiv.org/pdf/1909.03862.pdf

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.