Corpus ID: 36266696

Joint Matrix-Tensor Factorization for Knowledge Base Inference

@article{Jain2017JointMF,
  title={Joint Matrix-Tensor Factorization for Knowledge Base Inference},
  author={Prachi Jain and Shikhar Murty and Mausam and Soumen Chakrabarti},
  journal={ArXiv},
  year={2017},
  volume={abs/1706.00637}
}
  • Prachi Jain, Shikhar Murty, +1 author Soumen Chakrabarti
  • Published 2017
  • Computer Science
  • ArXiv
  • While several matrix factorization (MF) and tensor factorization (TF) models have been proposed for knowledge base (KB) inference, they have rarely been compared across various datasets. Is there a single model that performs well across datasets? If not, what characteristics of a dataset determine the performance of MF and TF models? Is there a joint TF+MF model that performs robustly on all datasets? We perform an extensive evaluation to compare popular KB inference models across popular… CONTINUE READING

    Tables and Topics from this paper

    References

    SHOWING 1-10 OF 39 REFERENCES
    Injecting Logical Background Knowledge into Embeddings for Relation Extraction
    • 177
    • PDF
    A Three-Way Model for Collective Learning on Multi-Relational Data
    • 1,034
    • Highly Influential
    • PDF
    Towards Combined Matrix and Tensor Factorization for Universal Schema Relation Extraction
    • 18
    • Highly Influential
    • PDF
    Embedding Entities and Relations for Learning and Inference in Knowledge Bases
    • 902
    • Highly Influential
    • PDF
    Translating Embeddings for Modeling Multi-relational Data
    • 2,499
    • Highly Influential
    • PDF
    Complex Embeddings for Simple Link Prediction
    • 768
    • PDF
    Reasoning With Neural Tensor Networks for Knowledge Base Completion
    • 1,272
    • PDF
    Relation Schema Induction using Tensor Factorization with Side Information
    • 18
    • PDF
    Typed Tensor Decomposition of Knowledge Bases for Relation Extraction
    • 153
    • PDF