arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.02484cs.CLcs.AIcs.LG
收藏

OodGAN:用于域外数据生成的生成对抗网络

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

Czech Technical University in Prague(布拉格捷克理工大学);Amazon Alexa AI(亚马逊Alexa AI)

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

摘要:

检测域外(OOD)话语对于健壮的对话系统至关重要。大多数对话系统都是在一个带注释的OOD数据池上训练的,以实现这一目标。然而,收集给定领域的带注释的OOD数据是一个昂贵的过程。为了缓解这个问题,以前的工作已经提出了基于生成对抗网络(GAN)的模型来自动生成给定域的OOD数据。然而,这些建议的模型不直接与文本。相反,它们使用文本的潜在空间,强制这些模型包含负责将文本编码到潜在空间并将其解码回来的组件,例如自动编码器。这些组件增加了模型的复杂性,使其难以进行训练。我们提出了OodGAN,一个基于顺序生成对抗网络(SeqGAN)的OOD数据生成模型。我们提出的模型直接作用于文本,因此无需包含自动编码器。使用OodGAN模型生成的OOD数据在ROSTD(FPR 0.95中相对改善67%)和OSQ数据集(FPR 0.95中相对改善28%)的OOD检测度量方面优于现有技术(Zheng等人,2020年)。

英文摘要:

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) (Zheng et al., 2020).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑