Corpus ID: 214727633

Procedural Reading Comprehension with Attribute-Aware Context Flow

@article{Amini2020ProceduralRC,
  title={Procedural Reading Comprehension with Attribute-Aware Context Flow},
  author={Aida Amini and Antoine Bosselut and B. D. Mishra and Yejin Choi and Hannaneh Hajishirzi},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.13878}
}
  • Aida Amini, Antoine Bosselut, +2 authors Hannaneh Hajishirzi
  • Published 2020
  • Computer Science
  • ArXiv
  • Procedural texts often describe processes (e.g., photosynthesis and cooking) that happen over entities (e.g., light, food). In this paper, we introduce an algorithm for procedural reading comprehension by translating the text into a general formalism that represents processes as a sequence of transitions over entity attributes (e.g., location, temperature). Leveraging pre-trained language models, our model obtains entity-aware and attribute-aware representations of the text by joint prediction… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 20 REFERENCES
    SQuAD: 100, 000+ Questions for Machine Comprehension of Text
    • 2,154
    • PDF
    Bidirectional Attention Flow for Machine Comprehension
    • 1,143
    • PDF
    Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
    • 742
    • PDF
    The NarrativeQA Reading Comprehension Challenge
    • 194
    • PDF
    Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension
    • 42
    • Highly Influential
    • PDF
    Tracking the World State with Recurrent Entity Networks
    • 140
    • PDF
    Query-Reduction Networks for Question Answering
    • 89
    • PDF