OodGAN: Generative Adversarial Network for Out-of-Domain Data Generation

Petr Marek, Vishal Ishwar Naik, Anuj Goyal, Vincent Auvray


Abstract
Detecting an Out-of-Domain (OOD) utterance is crucial for a robust dialog system. Most dialog systems are trained on a pool of annotated OOD data to achieve this goal. However, collecting the annotated OOD data for a given domain is an expensive process. To mitigate this issue, previous works have proposed generative adversarial networks (GAN) based models to generate OOD data for a given domain automatically. However, these proposed models do not work directly with the text. They work with the text’s latent space instead, enforcing these models to include components responsible for encoding text into latent space and decoding it back, such as auto-encoder. These components increase the model complexity, making it difficult to train. We propose OodGAN, a sequential generative adversarial network (SeqGAN) based model for OOD data generation. Our proposed model works directly on the text and hence eliminates the need to include an auto-encoder. OOD data generated using OodGAN model outperforms state-of-the-art in OOD detection metrics for ROSTD (67% relative improvement in FPR 0.95) and OSQ datasets (28% relative improvement in FPR 0.95)
Anthology ID:
2021.naacl-industry.30
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers
Month:
June
Year:
2021
Address:
Online
Editors:
Young-bum Kim, Yunyao Li, Owen Rambow
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
238–245
Language:
URL:
https://aclanthology.org/2021.naacl-industry.30
DOI:
10.18653/v1/2021.naacl-industry.30
Bibkey:
Cite (ACL):
Petr Marek, Vishal Ishwar Naik, Anuj Goyal, and Vincent Auvray. 2021. OodGAN: Generative Adversarial Network for Out-of-Domain Data Generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers, pages 238–245, Online. Association for Computational Linguistics.
Cite (Informal):
OodGAN: Generative Adversarial Network for Out-of-Domain Data Generation (Marek et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-industry.30.pdf
Video:
 https://aclanthology.org/2021.naacl-industry.30.mp4
Data
ROSTD