no code implementations • EMNLP 2020 • Joseph Fisher, Arpit Mittal, Dave Palfrey, Christos Christodoulopoulos
It has been shown that knowledge graph embeddings encode potentially harmful social biases, such as the information that women are more likely to be nurses, and men more likely to be bankers.
no code implementations • 5 Dec 2019 • Joseph Fisher, Dave Palfrey, Christos Christodoulopoulos, Arpit Mittal
It has recently been shown that word embeddings encode social biases, with a harmful impact on downstream tasks.
no code implementations • IJCNLP 2019 • Esma Balkir, Masha Naslidnyk, Dave Palfrey, Arpit Mittal
Bilinear models such as DistMult and ComplEx are effective methods for knowledge graph (KG) completion.
Ranked #18 on Link Prediction on FB15k
no code implementations • NAACL 2018 • Andrew Hopkinson, Amit Gurdasani, Dave Palfrey, Arpit Mittal
In this paper we introduce the notion of Demand-Weighted Completeness, allowing estimation of the completeness of a knowledge base with respect to how it is used.