Jay Pujara


2017

pdf bib
Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short
Jay Pujara | Eriq Augustine | Lise Getoor
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Knowledge graph (KG) embedding techniques use structured relationships between entities to learn low-dimensional representations of entities and relations. One prominent goal of these approaches is to improve the quality of knowledge graphs by removing errors and adding missing facts. Surprisingly, most embedding techniques have been evaluated on benchmark datasets consisting of dense and reliable subsets of human-curated KGs, which tend to be fairly complete and have few errors. In this paper, we consider the problem of applying embedding techniques to KGs extracted from text, which are often incomplete and contain errors. We compare the sparsity and unreliability of different KGs and perform empirical experiments demonstrating how embedding approaches degrade as sparsity and unreliability increase.

2016

pdf bib
Proceedings of the 5th Workshop on Automated Knowledge Base Construction
Jay Pujara | Tim Rocktaschel | Danqi Chen | Sameer Singh
Proceedings of the 5th Workshop on Automated Knowledge Base Construction

2015

pdf bib
RELLY: Inferring Hypernym Relationships Between Relational Phrases
Adam Grycner | Gerhard Weikum | Jay Pujara | James Foulds | Lise Getoor
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing