Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short

@inproceedings{Pujara2017SparsityAN,
  title={Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short},
  author={J. Pujara and Eriq Augustine and L. Getoor},
  booktitle={EMNLP},
  year={2017}
}
  • J. Pujara, Eriq Augustine, L. Getoor
  • Published in EMNLP 2017
  • Computer Science
  • 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… CONTINUE READING
    38 Citations

    Figures, Tables, and Topics from this paper

    Adaptive knowledge subgraph ensemble for robust and trustworthy knowledge graph completion
    • 3
    • Highly Influenced
    • PDF
    A Hybrid Model for Learning Embeddings and Logical Rules Simultaneously from Knowledge Graphs
    • S. Suresh, J. Neville
    • Computer Science
    • 2020 IEEE International Conference on Data Mining (ICDM)
    • 2020
    • PDF
    Rule-enhanced Noisy Knowledge Graph Embedding via Low-quality Error Detection
    • Y. Hong, C. Bu, T. Jiang
    • Computer Science
    • 2020 IEEE International Conference on Knowledge Graph (ICKG)
    • 2020
    • 1
    Embedding Uncertain Knowledge Graphs
    • 19
    • PDF
    Revisiting Evaluation of Knowledge Base Completion Models
    • 4
    • PDF
    NOIGAN: NOISE AWARE KNOWLEDGE GRAPH EMBEDDING
    • 2019
    IterefinE: Iterative KG Refinement Embeddings using Symbolic Knowledge
    • PDF

    References

    SHOWING 1-10 OF 18 REFERENCES
    Holographic Embeddings of Knowledge Graphs
    • 558
    • Highly Influential
    • PDF
    Translating Embeddings for Modeling Multi-relational Data
    • 2,566
    • Highly Influential
    • PDF
    A Review of Relational Machine Learning for Knowledge Graphs
    • 850
    • Highly Influential
    • PDF
    STransE: a novel embedding model of entities and relationships in knowledge bases
    • 130
    • Highly Influential
    • PDF
    Learning Entity and Relation Embeddings for Knowledge Graph Completion
    • 1,321
    • PDF
    Knowledge Graph Embedding by Translating on Hyperplanes
    • 1,281
    • Highly Influential
    Knowledge vault: a web-scale approach to probabilistic knowledge fusion
    • 1,114
    • PDF
    Using Semantics & Statistics to Turn Data into Knowledge
    • 5
    • PDF
    Reasoning With Neural Tensor Networks for Knowledge Base Completion
    • 1,286
    • PDF
    A Three-Way Model for Collective Learning on Multi-Relational Data
    • 1,052
    • PDF