Corpus ID: 53113673

Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension

@article{Das2019BuildingDK,
  title={Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension},
  author={Rajarshi Das and Tsendsuren Munkhdalai and Xingdi Yuan and Adam Trischler and A. McCallum},
  journal={ArXiv},
  year={2019},
  volume={abs/1810.05682}
}
We propose a neural machine-reading model that constructs dynamic knowledge graphs from procedural text. [...] Key Result We present some evidence that the model's knowledge graphs help it to impose commonsense constraints on its predictions.Expand
50 Citations
A Heterogeneous Graph with Factual, Temporal and Logical Knowledge for Question Answering Over Dynamic Contexts
  • 1
  • Highly Influenced
  • PDF
Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs
  • Highly Influenced
  • PDF
Predicting State Changes in Procedural Text using Analogical Question Answering
  • 4
  • Highly Influenced
  • PDF
DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs
  • 23
  • PDF
Understanding Procedural Text using Interactive Entity Networks
  • PDF
Dynamic Knowledge Graph Construction for Zero-shot Commonsense Question Answering
  • 19
  • PDF
Effective Use of Transformer Networks for Entity Tracking
  • 5
  • PDF
Knowledge-Aware Procedural Text Understanding with Multi-Stage Training
  • 1
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 26 REFERENCES
Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension
  • 52
  • Highly Influential
  • PDF
Modeling Biological Processes for Reading Comprehension
  • 137
  • PDF
Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks
  • 90
  • PDF
Bidirectional Attention Flow for Machine Comprehension
  • 1,329
  • Highly Influential
  • PDF
Reasoning about Actions and State Changes by Injecting Commonsense Knowledge
  • 46
  • Highly Influential
  • PDF
Zero-Shot Relation Extraction via Reading Comprehension
  • 169
  • Highly Influential
  • PDF
Neural architectures for open-type relation argument extraction
  • 12
  • PDF
Reading Wikipedia to Answer Open-Domain Questions
  • 841
  • Highly Influential
  • PDF
QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
  • 543
  • PDF
RelNet: End-to-end Modeling of Entities & Relations
  • 20
  • PDF
...
1
2
3
...