Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols

  title={Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols},
  author={Prachi Jain and Sushant Rathi and Mausam and Soumen Chakrabarti},
  • Prachi Jain, Sushant Rathi, +1 author Soumen Chakrabarti
  • Published in EMNLP 2020
  • Computer Science
  • Temporal knowledge bases associate relational (s,r,o) triples with a set of times (or a single time instant) when the relation is valid. While time-agnostic KB completion (KBC) has witnessed significant research, temporal KB completion (TKBC) is in its early days. In this paper, we consider predicting missing entities (link prediction) and missing time intervals (time prediction) as joint TKBC tasks where entities, relations, and time are all embedded in a uniform, compatible space. We present… CONTINUE READING

    Figures and Tables from this paper


    Recurrent Event Network for Reasoning over Temporal Knowledge Graphs
    • 22
    • Highly Influential
    Encoding Temporal Information for Time-Aware Link Prediction
    • 37
    • Highly Influential
    • PDF
    Learning Sequence Encoders for Temporal Knowledge Graph Completion
    • 52
    • Highly Influential
    • PDF
    Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
    • 127
    • PDF
    Towards Time-Aware Knowledge Graph Completion
    • 36
    • Highly Influential
    • PDF
    Knowledge Graph Embedding via Dynamic Mapping Matrix
    • 580
    • PDF
    Diachronic Embedding for Temporal Knowledge Graph Completion
    • 30
    • PDF
    Tensor Decompositions for temporal knowledge base completion
    • 11
    • Highly Influential
    • PDF