Reasoning about Actions and State Changes by Injecting Commonsense Knowledge

@article{Tandon2018ReasoningAA,
  title={Reasoning about Actions and State Changes by Injecting Commonsense Knowledge},
  author={Niket Tandon and Bhavana Dalvi and Joel Grus and Wen-tau Yih and Antoine Bosselut and Peter Clark},
  journal={ArXiv},
  year={2018},
  volume={abs/1808.10012}
}
  • Niket Tandon, Bhavana Dalvi, +3 authors Peter Clark
  • Published 2018
  • Computer Science
  • ArXiv
  • Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can be answered. [...] Key Method Unlike earlier methods, we treat the problem as a neural structured prediction task, allowing hard and soft constraints to steer the model away from unlikely predictions. We show that the new model significantly outperforms earlier systems on a benchmark dataset for procedural text…Expand Abstract

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 34 CITATIONS

    Be Consistent! Improving Procedural Text Comprehension using Label Consistency

    VIEW 5 EXCERPTS
    CITES BACKGROUND, RESULTS & METHODS

    A Heterogeneous Graph with Factual, Temporal and Logical Knowledge for Question Answering Over Dynamic Contexts

    VIEW 11 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 6 Highly Influenced Citations

    • Averaged 11 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 25 REFERENCES