Mitigating the Effect of Out-of-Vocabulary Entity Pairs in Matrix Factorization for KB Inference

@inproceedings{Jain2018MitigatingTE,
  title={Mitigating the Effect of Out-of-Vocabulary Entity Pairs in Matrix Factorization for KB Inference},
  author={Prachi Jain and Shikhar Murty and Mausam and Soumen Chakrabarti},
  booktitle={IJCAI},
  year={2018}
}
  • Prachi Jain, Shikhar Murty, +1 author Soumen Chakrabarti
  • Published in IJCAI 2018
  • Computer Science
  • This paper analyzes the varied performance of Matrix Factorization (MF) on the related tasks of relation extraction and knowledge-base completion, which have been unified recently into a single framework of knowledge-base inference (KBI) [Toutanova et al., 2015]. We first propose a new evaluation protocol that makes comparisons between MF and Tensor Factorization (TF) models fair. We find that this results in a steep drop in MF performance. Our analysis attributes this to the high out-of… CONTINUE READING
    4 Citations
    Type-Sensitive Knowledge Base Inference Without Explicit Type Supervision
    • 17
    • PDF
    Open Information Extraction from Question-Answer Pairs
    • 3
    • PDF

    References

    SHOWING 1-10 OF 41 REFERENCES
    Type-Sensitive Knowledge Base Inference Without Explicit Type Supervision
    • 17
    • PDF
    Embedding Entities and Relations for Learning and Inference in Knowledge Bases
    • 908
    • Highly Influential
    • PDF
    Relation Schema Induction using Tensor Factorization with Side Information
    • 18
    • PDF
    Knowledge Graph Embedding: A Survey of Approaches and Applications
    • 611
    • PDF