Explanipedia

Debiasing knowledge graph embeddings Open

Joseph B. Fisher, Arpit Mittal, Dave Palfrey, Christos Christodoulopoulos · 2020

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. As graph embeddings begin to be used more widel…

Measuring Social Bias in Knowledge Graph Embeddings Open

Joseph B. Fisher, Dave Palfrey, Christos Christodoulopoulos, Arpit Mittal · 2019

It has recently been shown that word embeddings encode social biases, with a harmful impact on downstream tasks. However, to this point there has been no similar work done in the field of graph embeddings. We present the first study on soc…

Using Pairwise Occurrence Information to Improve Knowledge Graph Completion on Large-Scale Datasets Open

Esma Balkır, Masha Naslidnyk, Dave Palfrey, Arpit Mittal · 2019

Bilinear models such as DistMult and ComplEx are effective methods for knowledge graph (KG) completion. However, they require large batch sizes, which becomes a performance bottleneck when training on large scale datasets due to memory con…

Using Pairwise Occurrence Information to Improve Knowledge Graph Completion on Large-Scale Datasets Open

Esma Balkır, Masha Naslidnyk, Dave Palfrey, Arpit Mittal · 2019

Esma Balkir, Masha Naslidnyk, Dave Palfrey, Arpit Mittal. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Demand-Weighted Completeness Prediction for a Knowledge Base Open

Andrew Hopkinson, Amit Gurdasani, Dave Palfrey, Arpit Mittal · 2018

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. Defining an entity by its classes, we employ usage data to predict the distr…

Dave Palfrey YOU? Author Swipe