A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space

Hong Xu, Keqing He, Yuanmeng Yan, Sihong Liu, Zijun Liu, Weiran Xu


Abstract
Detecting out-of-domain (OOD) input intents is critical in the task-oriented dialog system. Different from most existing methods that rely heavily on manually labeled OOD samples, we focus on the unsupervised OOD detection scenario where there are no labeled OOD samples except for labeled in-domain data. In this paper, we propose a simple but strong generative distance-based classifier to detect OOD samples. We estimate the class-conditional distribution on feature spaces of DNNs via Gaussian discriminant analysis (GDA) to avoid over-confidence problems. And we use two distance functions, Euclidean and Mahalanobis distances, to measure the confidence score of whether a test sample belongs to OOD. Experiments on four benchmark datasets show that our method can consistently outperform the baselines.
Anthology ID:
2020.coling-main.125
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1452–1460
Language:
URL:
https://aclanthology.org/2020.coling-main.125
DOI:
10.18653/v1/2020.coling-main.125
Bibkey:
Cite (ACL):
Hong Xu, Keqing He, Yuanmeng Yan, Sihong Liu, Zijun Liu, and Weiran Xu. 2020. A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1452–1460, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space (Xu et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.coling-main.125.pdf
Data
SNIPS