Out-of-domain Detection based on Generative Adversarial Network
- Title
- Out-of-domain Detection based on Generative Adversarial Network
- Authors
- Seonghan, Ryu; KOO, SANG JUN; HWANJO, YU; LEE, GARY GEUNBAE
- Date Issued
- 2018-11-04
- Publisher
- EMNLP
- Abstract
- The main goal of this paper is to develop out-of-domain (OOD) detection for dialog systems. We propose to use only in-domain (IND) sentences to build a generative adversarial network (GAN) of which the discriminator generates low scores for OOD sentences. To improve basic GANs, we apply feature matching loss in the discriminator, use domain-category analysis as an additional task in the discriminator, and remove the biases in the generator. Thereby, we reduce the huge effort of collecting OOD sentences for training OOD detection. For evaluation, we experimented OOD detection on a multi-domain dialog system. The experimental results showed the proposed method was most accurate compared to the existing methods. © 2018 Association for Computational Linguistics
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/94554
- ISSN
- 0000-0000
- Article Type
- Conference
- Citation
- Empirical Methods in Natural Language Processing, page. 714 - 718, 2018-11-04
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.