Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension

@article{Dalvi2018TrackingSC,
  title={Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension},
  author={Bhavana Dalvi and Lifu Huang and Niket Tandon and Wen-tau Yih and Peter F. Clark},
  journal={ArXiv},
  year={2018},
  volume={abs/1805.06975}
}
We present a new dataset and models for comprehending paragraphs about processes (e.g., photosynthesis), an important genre of text describing a dynamic world. The new dataset, ProPara, is the first to contain natural (rather than machine-generated) text about a changing world along with a full annotation of entity states (location and existence) during those changes (81k datapoints). The end-task, tracking the location and existence of entities through the text, is challenging because the… CONTINUE READING
19
Twitter Mentions

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

Key Quantitative Results

  • The new models improve accuracy by up to 19%.

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 15 CITATIONS

Be Consistent! Improving Procedural Text Comprehension using Label Consistency

  • NAACL-HLT
  • 2019
VIEW 4 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Tracking Discrete and Continuous Entity State for Process Understanding

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Reasoning about Actions and State Changes by Injecting Commonsense Knowledge

VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Step Semantics : Representations for State Changes in Natural Language

VIEW 4 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 27 REFERENCES