Be Consistent! Improving Procedural Text Comprehension using Label Consistency

@article{Du2019BeCI,
  title={Be Consistent! Improving Procedural Text Comprehension using Label Consistency},
  author={X. Du and Bhavana Dalvi Mishra and Niket Tandon and Antoine Bosselut and Wen-tau Yih and P. Clark and Claire Cardie},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.08942}
}
Our goal is procedural text comprehension, namely tracking how the properties of entities (e.g., their location) change with time given a procedural text (e.g., a paragraph about photosynthesis, a recipe. [...] Key Method We present a new learning framework that leverages label consistency during training, allowing consistency bias to be built into the model. Evaluation on a standard benchmark dataset for procedural text, ProPara (Dalvi et al., 2018), shows that our approach significantly improves prediction…Expand
12 Citations
Procedural Reasoning Networks for Understanding Multimodal Procedures
  • 6
  • PDF
Structured Tuning for Semantic Role Labeling
  • 3
  • PDF
Measuring and Improving Consistency in Pretrained Language Models
  • 1
  • PDF
Enabling Interactive Answering of Procedural Questions
  • PDF
Augmenting Neural Networks with First-order Logic
  • 28
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 27 REFERENCES
Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension
  • 52
  • PDF
Reasoning about Actions and State Changes by Injecting Commonsense Knowledge
  • 45
  • PDF
Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
  • 50
  • Highly Influential
  • PDF
A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
  • 434
  • PDF
Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
  • 800
  • PDF
Mise en Place: Unsupervised Interpretation of Instructional Recipes
  • 64
  • PDF
Modeling Biological Processes for Reading Comprehension
  • 137
  • PDF
Globally Coherent Text Generation with Neural Checklist Models
  • 139
  • PDF
AllenNLP: A Deep Semantic Natural Language Processing Platform
  • 607
  • Highly Influential
  • PDF
...
1
2
3
...