@inproceedings{marek-etal-2021-oodgan,
    title = "{O}od{GAN}: Generative Adversarial Network for Out-of-Domain Data Generation",
    author = "Marek, Petr  and
      Naik, Vishal Ishwar  and
      Goyal, Anuj  and
      Auvray, Vincent",
    editor = "Kim, Young-bum  and
      Li, Yunyao  and
      Rambow, Owen",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.naacl-industry.30/",
    doi = "10.18653/v1/2021.naacl-industry.30",
    pages = "238--245",
    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)"
}