TL;DR通过自动化方法,提出了一个名为 EDC 的三阶段框架,能够从输入文本中提取高质量的三元组,并解决了以往方法在应对大型复杂模式时的困难,同时引入了训练部分以改进模型的抽取性能。
Abstract
In this work, we are interested in automated methods for knowledge graph
creation (KGC) from input text. Progress on large language models (LLMs) has
prompted a series of recent works applying them to KGC, e.g.,