论文标题
将特定于任务的概念知识纳入脚本学习
Incorporating Task-specific Concept Knowledge into Script Learning
论文作者
论文摘要
在本文中，我们提出了俄罗斯方块，这是一个面向目标脚本完成的新任务。与以前的工作不同，它考虑了更现实和一般的设置，其中输入不仅包括目标，还包括其他用户上下文，包括偏好和历史记录。为了解决这个问题，我们提出了一种新颖的方法，该方法使用两种技术来提高性能：（1）概念提示，以及（2）面向脚本的对比度学习，以解决阶跃重复和幻觉问题。在基于Wikihow的数据集中，我们发现两种方法都可以提高性能。数据集，存储库和模型将公开使用，以促进对这项新任务的进一步研究。
In this paper, we present Tetris, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including preferences and history. To address this problem, we propose a novel approach, which uses two techniques to improve performance: (1) concept prompting, and (2) script-oriented contrastive learning that addresses step repetition and hallucination problems. On our WikiHow-based dataset, we find that both methods improve performance. The dataset, repository, and models will be publicly available to facilitate further research on this new task.
