LINQS

STATISTICAL RELATIONAL LEARNING GROUP @ UMD



 

Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short

Jay Pujara, Eriq Augustine, Lise Getoor
Conference on Empirical Methods in Natural Language Processing (EMNLP) - 2017
Download the publication : pujara-emnlp17.pdf [694Ko]  
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.

BibTex references

@InProceedings{pujara:emnlp17,
  author       = "Pujara, Jay and Augustine, Eriq and Getoor, Lise",
  title        = "Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short",
  booktitle    = "Conference on Empirical Methods in Natural Language Processing (EMNLP)",
  year         = "2017",
}

Other publications in the database