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}
}
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
45 Citations
Predicting State Changes in Procedural Text using Analogical Question Answering
  • 4
  • Highly Influenced
  • PDF
Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text
  • 6
  • PDF
Procedural Reasoning Networks for Understanding Multimodal Procedures
  • 6
  • PDF
Social Commonsense Reasoning with Multi-Head Knowledge Attention
  • 1
  • PDF
Be Consistent! Improving Procedural Text Comprehension using Label Consistency
  • 12
  • PDF
Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
  • 50
  • Highly Influenced
  • PDF
Understanding Procedural Text using Interactive Entity Networks
  • Highly Influenced
  • PDF
WIQA: A dataset for "What if..." reasoning over procedural text
  • 14
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 25 REFERENCES
What Happened? Leveraging VerbNet to Predict the Effects of Actions in Procedural Text
  • 11
  • PDF
Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension
  • 52
  • PDF
Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
  • 800
  • PDF
Mise en Place: Unsupervised Interpretation of Instructional Recipes
  • 64
  • PDF
Learning Biological Processes with Global Constraints
  • 17
  • PDF
Simulating Action Dynamics with Neural Process Networks
  • 63
  • PDF
Tracking the World State with Recurrent Entity Networks
  • 152
  • Highly Influential
  • PDF
Bidirectional Attention Flow for Machine Comprehension
  • 1,306
  • PDF
Neural Semantic Parsing with Type Constraints for Semi-Structured Tables
  • 137
  • PDF
...
1
2
3
...