Insufficient Data Can Also Rock! Learning to Converse Using Smaller Data with Augmentation

Li, Juntao1,2; Qiu, Lisong1,2; Tang, Bo3; Chen, Dongmin1; Zhao, Dongyan1,2; Yan, Rui1,2

2019

THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE

6698-6705

2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA

ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE

Recent successes of open-domain dialogue generation mainly rely on the advances of deep neural networks. The effectiveness of deep neural network models depends on the amount of training data. As it is laboursome and expensive to acquire a huge amount of data in most scenarios, how to effectively utilize existing data is the crux of this issue. In this paper, we use data augmentation techniques to improve the performance of neural dialogue models on the condition of insufficient data. Specifically, we propose a novel generative model to augment existing data, where the conditional variational autoencoder (CVAE) is employed as the generator to output more training data with diversified expressions. To improve the correlation of each augmented training pair, we design a discriminator with adversarial training to supervise the augmentation process. Moreover, we thoroughly investigate various data augmentation schemes for neural dialogue system with generative models, both GAN and CVAE. Experimental results on two open corpora, Weibo and Twitter, demonstrate the superiority of our proposed data augmentation model.

其他

英语

CPCI-S ; EI

Guangdong Natural Science Foundation[2018A030310129]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic

WOS:000486572501029

20203509102082

Speech processing ; Neural network models ; Social networking (online)

Ergonomics and Human Factors Engineering:461.4 ; Computer Software, Data Handling and Applications:723 ; Artificial Intelligence:723.4 ; Speech:751.5

Web of Science

1.Peking Univ, Acad Adv Interdisciplinary Studies, Ctr Data Sci, Beijing, Peoples R China
2.Peking Univ, Inst Comp Sci & Technol, Beijing, Peoples R China
3.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Peoples R China

Li, Juntao,Qiu, Lisong,Tang, Bo,et al. Insufficient Data Can Also Rock! Learning to Converse Using Smaller Data with Augmentation[C]. 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA:ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE,2019:6698-6705.