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 Sebastian Riedel},
  year={2018}
}
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

Citations

Publications citing this paper.
SHOWING 1-10 OF 17 CITATIONS

FEVER Breaker’s Run of Team NbAuzDrLqg

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Extract and Aggregate: A Novel Domain-Independent Approach to Factual Data Verification

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

BERT for Evidence Retrieval and Claim Verification

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Automated Fact Checking in the News Room

VIEW 2 EXCERPTS
CITES METHODS & BACKGROUND

Fact-Checking Fake News

  • Bart Melman
  • 2019
VIEW 2 EXCERPTS
CITES BACKGROUND & METHODS

GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 12 REFERENCES

Enhanced LSTM for Natural Language Inference

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Deep contextualized word representations

VIEW 1 EXCERPT

Washington post fake news story blurs the definition of fake news

  • David Uberti.
  • Columbia Journalism Review.
  • 2016
VIEW 1 EXCERPT