From Plots to Endings:A Reinforced Pointer Generator for Story Ending Generation

摘要：

　　We introduce a new task named Story Ending Generation(SEG),which aims at generating a coherent story ending from a sequence of story plot.We propose a framework consisting of a Generator and a Reward Manager for this task.The Generator follows the pointer-generator network with coverage mechanism to deal with out-of-vocabulary(OOV)and repetitive words.Moreover,a mixed loss method is introduced to enable the Generator to produce story endings of high semantic relevance with story plots.In the Reward Manager,the reward is computed to fine-tune the Generator with policy-gradient reinforcement learning(PGRL).We conduct experiments on the recentlyintroduced ROCStories Corpus.We evaluate our model in both automatic evaluation and human evaluation.Experimental results show that our model exceeds the sequence-to-sequence baseline model by 15.75%and 13.57%in terms of CIDEr and consistency score respectively.

关键词： Story Ending Generation Pointer-generator Policy gradient

作者: Yan Zhao Lu Liu Chunhua Liu Ruoyao Yang Dong Yu

作者单位: Beijing Language and Culture University,Beijing,China Beijing Language and Culture University,Beijing,China;Beijing Advanced Innovation for Language Resou

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 51-63

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）