Abstract: Factual knowledge graphs (KGs) such as DBpedia and Wikidata have served as
part of various downstream tasks and are also widely adopted by artificial
intelligence research communities as benchmark datasets. However, we found
these KGs to be surprisingly noisy. In this study, we question the quality of
these KGs, where the typing error rate is estimated to be 27% for
coarse-grained types on average, and even 73% for certain fine-grained types.
In pursuit of solutions, we propose an active typing error detection algorithm
that maximizes the utilization of both gold and noisy labels. We also
comprehensively discuss and compare unsupervised, semi-supervised, and
supervised paradigms to deal with typing errors in factual KGs. The outcomes of
this study provide guidelines for researchers to use noisy factual KGs. To help
practitioners deploy the techniques and conduct further research, we published
our code and data.