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.- Anthology ID:
- D18-1077
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 714–718
- Language:
- URL:
- https://aclanthology.org/D18-1077
- DOI:
- 10.18653/v1/D18-1077
- Cite (ACL):
- Seonghan Ryu, Sangjun Koo, Hwanjo Yu, and Gary Geunbae Lee. 2018. Out-of-domain Detection based on Generative Adversarial Network. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 714–718, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Out-of-domain Detection based on Generative Adversarial Network (Ryu et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/D18-1077.pdf