Draft and edit: Automatic storytelling through multi-pass hierarchical conditional variational autoencoder

Yu，Meng Hsuan1; Li，Juntao1,3; Liu，Danyang1,2; Tang，Bo4; Zhang，Haisong5; Zhao，Dongyan1,3; Yan，Rui1,2,3

2020

34th AAAI Conference on Artificial Intelligence / 32nd Innovative Applications of Artificial Intelligence Conference / 10th AAAI Symposium on Educational Advances in Artificial Intelligence

2159-5399

2374-3468

AAAI 2020 - 34th AAAI Conference on Artificial Intelligence

34

1741-1748

FEB 07-12, 2020

null,New York,NY

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

ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE

Automatic Storytelling has consistently been a challenging area in the field of natural language processing. Despite considerable achievements have been made, the gap between automatically generated stories and human-written stories is still significant. Moreover, the limitations of existing automatic storytelling methods are obvious, e.g., the consistency of content, wording diversity. In this paper, we proposed a multi-pass hierarchical conditional variational autoencoder model to overcome the challenges and limitations in existing automatic storytelling models. While the conditional variational autoencoder (CVAE) model has been employed to generate diversified content, the hierarchical structure and multi-pass editing scheme allow the story to create more consistent content. We conduct extensive experiments on the ROCStories Dataset. The results verified the validity and effectiveness of our proposed model and yields substantial improvement over the existing state-of-the-art approaches.

其他

英语

EI ; CPCI-S

National Key Research and Development Program of China[2017YFC0804001] ; National Science Foundation of China (NSFC)[61876196,61672058,61802163] ; Guangdong Natural Science Foundation[2018A030310129] ; PCL Future Regional Network Facilities for Large-scale Experiments and Applications[PCL2018KP001]

Computer Science ; Education & Educational Research

Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Education, Scientific Disciplines

WOS:000667722801099

20210509848655

Learning systems ; Natural language processing systems

Data Processing and Image Processing:723.2 ; Artificial Intelligence:723.4

2-s2.0-85095866116

Scopus

1.Wangxuan Institute of Computer Technology,Peking University,Beijing,China
2.Key Laboratory of Artificial Intelligence,Ministry of Education,Shanghai Jiao Tong University,Shanghai,200240,China
3.Center for Data Science,AAIS,Peking University,Beijing,China
4.Department of Computer Science and Engineering,Southern University of Science and Technology,
5.Tencent AI Lab,

Yu，Meng Hsuan,Li，Juntao,Liu，Danyang,et al. Draft and edit: Automatic storytelling through multi-pass hierarchical conditional variational autoencoder[C]. 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA:ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE,2020:1741-1748.