Answering Complex Questions Using Open Information Extraction

@inproceedings{Khot2017AnsweringCQ,
  title={Answering Complex Questions Using Open Information Extraction},
  author={Tushar Khot and Ashish Sabharwal and Peter Clark},
  booktitle={ACL},
  year={2017}
}
While there has been substantial progress in factoid question-answering (QA), answering complex questions remains challenging, typically requiring both a large body of knowledge and inference techniques. Open Information Extraction (Open IE) provides a way to generate semi-structured knowledge for QA, but to date such knowledge has only been used to answer simple questions with retrieval-based methods. We overcome this limitation by presenting a method for reasoning with Open IE knowledge… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • We demonstrate that TUPLEINF significantly outperforms TABLEILP by 11.8% on a broad set of over 1,300 science questions, without requiring manually curated tables, using a substantially simpler ILP formulation, and generalizing well to higher grade levels.

Citations

Publications citing this paper.
SHOWING 1-10 OF 32 CITATIONS

Reasoning-Driven Question-Answering for Natural Language Understanding

Daniel Khashabi
  • ArXiv
  • 2019
VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Improving Question Answering with External Knowledge

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.