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 2204.05939cs.CLcs.AI
收藏

从预训练的语言模型中挖掘逻辑事件模式

Mining Logical Event Schemas From Pre-Trained Language Models

University of Rochester(罗切斯特大学)

Lane Lawley, Lenhart Schubert

摘要:

我们提出了NESL(神经情节图式学习者),一个事件图式学习系统,结合了大语言模型,框架网络解析,一个强大的语言逻辑表示,和一组简单的行为模式,旨在引导学习过程。代替预先制作的故事语料库,我们的数据集是来自预先训练的语言模型的"情景样本"的连续馈送,然后将其解析为FrameNet框架,映射为简单的行为模式,并组合和概括为各种日常场景的复杂分层模式。我们表明,仔细采样的语言模型可以帮助强调刻板的情况下,不强调不相关的细节,并由此产生的模式比其他系统的学习情况更全面。

英文摘要:

We present NESL (the Neuro-Episodic Schema Learner), an event schema learning system that combines large language models, FrameNet parsing, a powerful logical representation of language, and a set of simple behavioral schemas meant to bootstrap the learning process. In lieu of a pre-made corpus of stories, our dataset is a continuous feed of "situation samples" from a pre-trained language model, which are then parsed into FrameNet frames, mapped into simple behavioral schemas, and combined and generalized into complex, hierarchical schemas for a variety of everyday scenarios. We show that careful sampling from the language model can help emphasize stereotypical properties of situations and de-emphasize irrelevant details, and that the resulting schemas specify situations more comprehensively than those learned by other systems.

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。

↑