Corpus ID: 226956103

Medical symptom recognition from patient text: An active learning approach for long-tailed multilabel distributions

@article{Mottaghi2020MedicalSR,
  title={Medical symptom recognition from patient text: An active learning approach for long-tailed multilabel distributions},
  author={A. Mottaghi and P. Sarma and X. Amatriain and Serena Yeung and Anitha Kannan},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.06874}
}
We study the problem of medical symptoms recognition from patient text, for the purposes of gathering pertinent information from the patient (known as history-taking). We introduce an active learning method that leverages underlying structure of a continually refined, learned latent space to select the most informative examples to label. This enables the selection of the most informative examples that progressively increases the coverage on the universe of symptoms via the learned model… Expand

Figures from this paper

Active learning for medical code assignment

References

SHOWING 1-10 OF 28 REFERENCES
Active learning for hierarchical multi-label classification
Mining Multi-label Data
Effective active learning strategy for multi-label learning
Active Learning Literature Survey
Support Vector Machine Active Learning with Applications to Text Classification
Deep Bayesian Active Learning with Image Data
Variational Adversarial Active Learning
Active Learning for Convolutional Neural Networks: A Core-Set Approach
...
1
2
3
...