Story Ending Generation (SEG) is a challenging task in natural language generation. Recently, methods based on Pre-trained Language Models (PLM) have achieved great prosperity, which can produce fluent and coherent story endings. However, the pre-training objective of PLM-based methods is unable to model the consistency between story context and ending. The goal of this paper is to adopt contrastive learning to generate endings more consistent with story context, while there are two main challenges in contrastive learning of SEG. First is the negative sampling of wrong endings inconsistent with story contexts. The second challenge is the adaptation of contrastive learning for SEG. To address these two issues, we propose a novel Contrastive Learning framework for Story Ending Generation (CLSEG), which has two steps: multi-aspect sampling and story-specific contrastive learning. Particularly, for the first issue, we utilize novel multi-aspect sampling mechanisms to obtain wrong endings considering the consistency of order, causality, and sentiment. To solve the second issue, we well-design a story-specific contrastive training strategy that is adapted for SEG. Experiments show that CLSEG outperforms baselines and can produce story endings with stronger consistency and rationality.
Dagger Behind Smile: Fool LLMs with a Happy Ending Story
S-Lab, Nanyang Technological University, Singapore(南洋理工大学新加坡分校S实验室);College of Computing and Data Science, Nanyang Technological University, Singapore(南洋理工大学计算机与数据科学学院)
StorySpark: Module-wise Evolutionary Search for Story Premise Generation
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Renmin University of China(中国人民大学);Shandong University(山东大学);Institute of Deep Perception Technology, JITRI(JITRI深度感知技术研究院)
An Ion Exchange Mechanism Inspired Story Ending Generator for Different Characters
University of Technology Sydney(悉尼科技大学);Deepblue Academy of Sciences(深蓝科学院);Beijing Institute of Technology(北京理工大学);University of Science and Technology Beijing(北京科技大学);Tongji University(同济大学);Macquarie University(麦考瑞大学)
The Challenge and Reward of Fair Play in Narrative: A Computational Approach
Department of Computer Science Hebrew University of Jerusalem(计算机科学系 Hebrew University of Jerusalem);Department of Law and Digital Humanities Hebrew University of Jerusalem(法律与数字人文系 Hebrew University of Jerusalem)
Sketch and Customize: A Counterfactual Story Generator
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Tencent AI Lab(腾讯人工智能实验室)
The Effect of Different Writing Tasks on Linguistic Style: A Case Study of the ROC Story Cloze Task
University of Washington(华盛顿大学);Allen Institute for Artificial Intelligence(艾伦人工智能研究所)
一个作家的风格不仅取决于个人特质,还取决于她的意图和精神状态。在本文中,我们展示了如何相同的写作任务的变体可以导致可测量的写作风格的差异。我们提出了一个基于故事完形填空任务的案例研究(Mostafazadeh et al.,2016 a),其中注释者被分配了具有不同约束的类似写作任务:(1)编写整个故事,(2)为给定的故事上下文添加故事结局,以及(3)为故事添加不连贯的结局。我们表明,一个简单的线性分类通知文体特征是能够成功区分这三种情况下,甚至不看的故事背景。此外,将我们的文体特征与语言模型预测相结合,达到了故事完形填空的最佳表现。我们的研究结果表明,不同的任务框架可以显着影响人们的写作方式。