Bridging Knowledge Gaps in Neural Entailment via Symbolic Models

@inproceedings{Kang2018BridgingKG,
  title={Bridging Knowledge Gaps in Neural Entailment via Symbolic Models},
  author={Dongyeop Kang and Tushar Khot and Ashutosh Sabharwal and Peter Clark},
  booktitle={EMNLP},
  year={2018}
}
Most textual entailment models focus on lexical gaps between the premise text and the hypothesis, but rarely on knowledge gaps. We focus on filling these knowledge gaps in the Science Entailment task, by leveraging an external structured knowledge base (KB) of science facts. Our new architecture combines standard neural entailment models with a knowledge lookup module. To facilitate this lookup, we propose a fact-level decomposition of the hypothesis, and verifying the resulting sub-facts… CONTINUE READING
Tweets
This paper has been referenced on Twitter 15 times. VIEW TWEETS

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • On the SciTail dataset, NSnet outperforms a simpler combination of the two predictions by 3% and the base entailment model by 5%.

References

Publications referenced by this paper.
SHOWING 1-10 OF 20 REFERENCES

Similar Papers

Loading similar papers…