Abstract
Event temporal relation (TempRel) is a primary subject of the event relation extraction task. However, the inherent ambiguity of TempRel increases the difficulty of the task. With the rise of prompt engineering, it is important to design effective prompt templates and verbalizers to extract relevant knowledge. The traditional manually designed templates struggle to extract precise temporal knowledge. This paper introduces a novel retrieval-augmented TempRel extraction approach, leveraging knowledge retrieved from large language models (LLMs) to enhance prompt templates and verbalizers. Our method capitalizes on the diverse capabilities of various LLMs to generate a wide array of ideas for template and verbalizer design. Our proposed method fully exploits the potential of LLMs for generation tasks and contributes more knowledge to our design. Empirical evaluations across three widely recognized datasets demonstrate the efficacy of our method in improving the performance of event temporal relation extraction tasks.
Abstract (translated)
事件时间关系(TempRel)是事件关系提取任务的主要研究对象。然而,TempRel固有的歧义性增加了任务的难度。随着提示工程的发展,设计有效的提示模板和语义器以提取相关知识非常重要。传统的自定义模板在提取精确的时间知识方面很难。本文介绍了一种新颖的基于检索增强的TempRel提取方法,利用来自大型语言模型(LLMs)的知识来增强提示模板和语义器。我们的方法利用各种LLM的多样性来生成模板和语义器设计的大量想法。我们所提出的方法充分发掘LLMs的生成任务潜力,并为我们的设计贡献了更多的知识。通过在三个广泛认可的数据集上进行实证评估,证明我们的方法在提高事件时间关系提取任务的性能方面非常有效。
URL
https://arxiv.org/abs/2403.15273