UCL Machine Reading Group: Four Factor Framework For Fact Finding (HexaF)

@inproceedings{Yoneda2018UCLMR,
  title={UCL Machine Reading Group: Four Factor Framework For Fact Finding (HexaF)},
  author={Takuma Yoneda and Jeff Mitchell and Johannes Welbl and Pontus Stenetorp and S. Riedel},
  year={2018}
}
  • Takuma Yoneda, Jeff Mitchell, +2 authors S. Riedel
  • Published 2018
  • Computer Science
  • In this paper we describe our 2 place FEVER shared-task system that achieved a FEVER score of 62.52% on the provisional test set (without additional human evaluation), and 65.41% on the development set. Our system is a four stage model consisting of document retrieval, sentence retrieval, natural language inference and aggregation. Retrieval is performed leveraging task-specific features, and then a natural language inference model takes each of the retrieved sentences paired with the claimed… CONTINUE READING
    38 Citations

    Figures, Tables, and Topics from this paper

    Revealing the Importance of Semantic Retrieval for Machine Reading at Scale
    • 38
    • PDF
    AttentiveChecker: A Bi-Directional Attention Flow Mechanism for Fact Verification
    • 2
    • PDF
    Unsupervised Question Answering for Fact-Checking
    • 5
    • PDF
    Simple Compounded-Label Training for Fact Extraction and Verification
    • 4
    • Highly Influenced
    • PDF
    Evidence Distilling for Fact Extraction and Verification
    • PDF
    LOREN: Logic Enhanced Neural Reasoning for Fact Verification
    • Highly Influenced
    • PDF
    Combining Fact Extraction and Verification with Neural Semantic Matching Networks
    • 78
    • PDF
    Reasoning Over Semantic-Level Graph for Fact Checking
    • 21
    • PDF

    References

    SHOWING 1-10 OF 11 REFERENCES
    SUMMA at TAC Knowledge Base Population Task 2017
    • 7
    • PDF
    FEVER: a large-scale dataset for Fact Extraction and VERification
    • 275
    • Highly Influential
    • PDF
    Enhanced LSTM for Natural Language Inference
    • 573
    • Highly Influential
    • PDF
    Glove: Global Vectors for Word Representation
    • 16,761
    • PDF
    Fact Checking: Task definition and dataset construction
    • 171
    • PDF
    A Decomposable Attention Model for Natural Language Inference
    • 813
    • PDF
    Deep contextualized word representations
    • 5,232
    • PDF
    Numeracy for Language Models: Evaluating and Improving their Ability to Predict Numbers
    • 20
    • PDF
    Rectified Linear Units Improve Restricted Boltzmann Machines
    • 9,869
    • PDF