The knowledge of scripts, common chains of events in stereotypical scenarios, is a valuable asset for task-oriented natural language understanding systems. We propose the Goal-Oriented Script Construction task, where a model produces a sequence of steps to accomplish a given goal. We pilot our task on the first multilingual script learning dataset supporting 18 languages collected from wikiHow, a website containing half a million how-to articles. For baselines, we consider both a generation-based approach using a language model and a retrieval-based approach by first retrieving the relevant steps from a large candidate pool and then ordering them. We show that our task is practical, feasible but challenging for state-of-the-art Transformer models, and that our methods can be readily deployed for various other datasets and domains with decent zero-shot performance.
翻译:脚本知识是陈规定型情景中常见的一系列事件,是面向任务的自然语言理解系统的宝贵资产。我们提议了以目标为导向的脚本构建任务,其中模型为实现既定目标提供一系列步骤。我们试行了第一个多语种脚本学习数据集,支持从WikiHow收集的18种语言。WikiHow网站包含50万多篇文章。关于基线,我们既考虑采用以代为基础的方法,也考虑采用以语言模式和检索为基础的方法,首先从大型候选人库中检索相关步骤,然后订购这些步骤。我们表明,我们的任务是实用的,可行,但对于最先进的变异模型来说具有挑战性,我们的方法可以很容易地用于其他各种数据集和领域,并且具有体面的零弹性能。