BriefGPT.xyz
Oct, 2020
语言模型是开放的知识图谱
Language Models are Open Knowledge Graphs
HTML
PDF
Chenguang Wang, Xiao Liu, Dawn Song
TL;DR
本论文介绍了如何使用预训练语言模型构建知识图谱，从而达到无须人类监督的效果，并通过比较人类创建的两个知识图谱，证明了构建的知识图谱的质量高，能够提供新的事实知识，并公开了相关代码和知识图谱。
Abstract
This paper shows how to construct
knowledge graphs
(KGs) from
pre-trained language models
(e.g., BERT, GPT-2/3), without human supervision. Popular KGs (e.g, Wikidata, NELL) are built in either a supervised or se
→