Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions

@inproceedings{Clark2016CombiningRS,
  title={Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions},
  author={Peter Clark and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Oyvind Tafjord and Peter D. Turney and Daniel Khashabi},
  booktitle={AAAI},
  year={2016}
}
What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background knowledge and interpret test questions, but did not improve upon an information retrieval (IR) baseline. In this paper, we describe an alternative approach that operates at three levels of representation and reasoning: information retrieval, corpus statistics, and simple inference over a semi… CONTINUE READING

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

Key Quantitative Results

  • We evaluate the methods on six years of unseen, unedited exam questions from the NY Regents Science Exam (using only non-diagram, multiple choice questions), and show that our overall system's score is 71.3%, an improvement of 23.8% (absolute) over the MLN-based method described in previous work.

Citations

Publications citing this paper.
SHOWING 1-10 OF 65 CITATIONS

Advances in Automatically Solving the ENEM

  • 2018 7th Brazilian Conference on Intelligent Systems (BRACIS)
  • 2018
VIEW 8 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Improving Machine Reading Comprehension with General Reading Strategies

VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Reasoning-Driven Question-Answering for Natural Language Understanding

Daniel Khashabi
  • ArXiv
  • 2019
VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2019

CITATION STATISTICS

  • 12 Highly Influenced Citations

  • Averaged 18 Citations per year from 2017 through 2019

References

Publications referenced by this paper.