arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.00087cs.CL
收藏

再论无监督关系抽取

Revisiting Unsupervised Relation Extraction

University of Manchester(曼彻斯特大学);The Alan Turing Institute(艾伦·图灵研究所)

Thy Thy Tran, Phong Le, Sophia Ananiadou

摘要:

无监督关系抽取(URE)从原始文本中抽取命名实体之间的关系,而无需手动标记数据和现有知识库(KB)。URE方法可以分为生成性和判别性方法,它们依赖于手工制作的特征或表面形式。然而,我们证明,通过仅使用命名实体来诱导关系类型,我们可以在两个流行的数据集上胜过现有的方法。我们进行比较和评估我们的研究结果与其他的URE技术,以确定在URE的重要功能。我们的结论是,实体类型提供了一个强大的归纳偏见的URE。

英文摘要:

Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs). URE methods can be categorised into generative and discriminative approaches, which rely either on hand-crafted features or surface form. However, we demonstrate that by using only named entities to induce relation types, we can outperform existing methods on two popular datasets. We conduct a comparison and evaluation of our findings with other URE techniques, to ascertain the important features in URE. We conclude that entity types provide a strong inductive bias for URE.

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。

↑