Zero-Shot Relation Extraction via Reading Comprehension

@article{Levy2017ZeroShotRE,
  title={Zero-Shot Relation Extraction via Reading Comprehension},
  author={Omer Levy and Minjoon Seo and Eunsol Choi and Luke S. Zettlemoyer},
  journal={ArXiv},
  year={2017},
  volume={abs/1706.04115}
}
We show that relation extraction can be reduced to answering simple reading comprehension questions, by associating one or more natural-language questions with each relation slot. This reduction has several advantages: we can (1) learn relation-extraction models by extending recent neural reading-comprehension techniques, (2) build very large training sets for those models by combining relation-specific crowd-sourced questions with distant supervision, and even (3) do zero-shot learning by… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 47 CITATIONS

Know What You Don't Know: Unanswerable Questions for SQuAD

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

QA4IE: A Question Answering Based Framework for Information Extraction

  • International Semantic Web Conference
  • 2018
VIEW 6 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Step 1 : Entity Recognition Step 3 : Question Answering System Answer List

  • 2018
VIEW 6 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Neural architectures for open-type relation argument extraction

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Zero-shot Relation Classification as Textual Entailment

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Code2vec: Learning Distributed Representations of Code

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Read + Verify: Machine Reading Comprehension with Unanswerable Questions

  • AAAI
  • 2018
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 22 REFERENCES