arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.09049cs.CL
收藏

CLSEG:故事结尾生成的对比学习

CLSEG: Contrastive Learning of Story Ending Generation

Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);University of Chinese Academy of Sciences(中国科学院大学)

Yuqiang Xie, Yue Hu, Luxi Xing, Yunpeng Li, Wei Peng, Ping Guo

摘要:

故事结尾生成是自然语言生成中的一项具有挑战性的任务。近年来,基于预训练语言模型(PLM)的方法取得了很大的发展,它可以产生流畅连贯的故事结局。然而,基于PLM的方法的预训练目标无法对故事上下文和结局之间的一致性进行建模。本文的目标是采用对比学习来生成更符合故事语境的结尾,而SEG的对比学习主要有两个挑战。第一,错误结局与故事背景不一致的负面抽样。第二个挑战是对比学习对SEG的适应。为了解决这两个问题,我们提出了一个新的对比学习框架的故事结尾生成(CLSEG),它有两个步骤:多方面的采样和特定的故事对比学习。特别是,对于第一个问题,我们利用新的多方面的采样机制,以获得错误的结局,考虑到顺序,因果关系和情感的一致性。为了解决第二个问题,我们精心设计了一个适合SEG的故事特定的对比训练策略。实验结果表明,CLSEG算法的性能优于基线算法,能够生成一致性和合理性更强的故事结局。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑