• Computer Science
  • Published in IJCAI 2016

Question Answering via Integer Programming over Semi-Structured Knowledge

@inproceedings{Khashabi2016QuestionAV,
  title={Question Answering via Integer Programming over Semi-Structured Knowledge},
  author={Daniel Khashabi and Tushar Khot and Ashish Sabharwal and Peter Clark and Oren Etzioni and Dan Roth},
  booktitle={IJCAI},
  year={2016}
}
Answering science questions posed in natural language is an important AI challenge. Answering such questions often requires non-trivial inference and knowledge that goes beyond factoid retrieval. Yet, most systems for this task are based on relatively shallow Information Retrieval (IR) and statistical correlation techniques operating on large unstructured corpora. We propose a structured inference system for this task, formulated as an Integer Linear Program (ILP), that answers natural language… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 50 CITATIONS

Reasoning-Driven Question-Answering for Natural Language Understanding

VIEW 14 EXCERPTS
CITES METHODS & BACKGROUND

Learning What is Essential in Questions

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS

RACE: Large-scale ReAding Comprehension Dataset From Examinations

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2019

CITATION STATISTICS

  • 5 Highly Influenced Citations

  • Averaged 16 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 38 REFERENCES

SCIP: solving constraint integer programs

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Recognizing Textual Entailment: Models and Applications

VIEW 5 EXCERPTS

Recognizing textual entailment : Rational , evaluation and approaches

  • I D O D A G A N, Okereke A.N, B E R N A R D O M A G N I N I
  • 2009
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

WordNet: a lexical database for English

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Appendix: Features in Solver Combination To combine the predictions from all the solvers, we learn a Logistic Regression model [Clark et al., 2016] that returns a probability for an answer

  • B chains
  • 2016