A General Framework for Information Extraction using Dynamic Span Graphs

@article{Luan2019AGF,
  title={A General Framework for Information Extraction using Dynamic Span Graphs},
  author={Yi Luan and Dave Wadden and Luheng He and Amy Shah and Mari Ostendorf and Hannaneh Hajishirzi},
  journal={CoRR},
  year={2019},
  volume={abs/1904.03296}
}
We introduce a general framework for several information extraction tasks that share span representations using dynamically constructed span graphs. The graphs are constructed by selecting the most confident entity spans and linking these nodes with confidenceweighted relation types and coreferences. The dynamic span graph allows coreference and relation type confidences to propagate through the graph to iteratively refine the span representations. This is unlike previous multitask frameworks… CONTINUE READING
Tweets
This paper has been referenced on Twitter 4 times. VIEW TWEETS

References

Publications referenced by this paper.
SHOWING 1-10 OF 38 REFERENCES

Similar Papers

Loading similar papers…