A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation

• Published in: Transactions of the Association for Computational Linguistics Vol. 8; pp. 93 - 108
• Main Authors: Guan, Jian, Huang, Fei, Zhao, Zhihao, Zhu, Xiaoyan, Huang, Minlie
• Format: Journal Article
• Language: English
• Published: One Rogers Street, Cambridge, MA 02142-1209, USA MIT Press 01.01.2020; MIT Press Journals, The; The MIT Press
• Subjects: Automatic text generation; Coherence; Fluency; Knowledge; Knowledge bases (artificial intelligence); Linguistics; Semantics
• ISSN: 2307-387X; 2307-387X
• DOI: 10.1162/tacl_a_00302

Story generation, namely, generating a reasonable story from a leading context, is an important but challenging task. In spite of the success in modeling fluency and local coherence, existing neural language generation models (e.g., GPT-2) still suffer from repetition, logic conflicts, and lack of long-range coherence in generated stories. We conjecture that this is because of the difficulty of associating relevant commonsense knowledge, understanding the causal relationships, and planning entities and events with proper temporal order. In this paper, we devise a knowledge-enhanced pretraining model for commonsense story generation. We propose to utilize commonsense knowledge from external knowledge bases to generate reasonable stories. To further capture the causal and temporal dependencies between the sentences in a reasonable story, we use multi-task learning, which combines a discriminative objective to distinguish true and fake stories during fine-tuning. Automatic and manual evaluation shows that our model can generate more reasonable stories than state-of-the-art baselines, particularly in terms of logic and global coherence.