Learning towards Selective Data Augmentation for Dialogue Generation


  • Xiuying Chen Computational Bioscience Research Center, KAUST
  • Mingzhe Li Ant Group
  • Jiayi Zhang Xiaomi AI Lab
  • Xiaoqiang Xia Xiaomi AI Lab
  • Chen Wei Xiaomi AI Lab
  • Jianwei Cui Xiaomi AI Lab
  • Xin Gao Computational Bioscience Research Center, KAUST
  • Xiangliang Zhang University of Notre Dame
  • Rui Yan Gaoling School of Artificial Intelligence, Renmin University of China




SNLP: Conversational AI/Dialogue Systems, SNLP: Generation


As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples. However, current data augmentation techniques on the dialog generation task mostly augment all cases in the training dataset without considering the intrinsic attributes between different cases. We argue that not all cases are beneficial for augmentation task, and the cases suitable for augmentation should obey the following two attributes: (1) low-quality (the dialog model cannot generate a high-quality response for the case), (2) representative (the case should represent the property of the whole dataset). Herein, we explore this idea by proposing a Selective Data Augmentation framework (SDA) for the response generation task. SDA employs a dual adversarial network to select the lowest quality and most representative data points for augmentation in one stage. Extensive experiments conducted on two publicly available datasets, i.e., DailyDialog and OpenSubtitles, show that our framework can improve the response generation performance with respect to various metrics




How to Cite

Chen, X., Li, M., Zhang, J., Xia, X., Wei, C., Cui, J., Gao, X., Zhang, X., & Yan, R. (2023). Learning towards Selective Data Augmentation for Dialogue Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(11), 12673-12681. https://doi.org/10.1609/aaai.v37i11.26491



AAAI Technical Track on Speech & Natural Language Processing