Constrained Semi-supervised Learning in the Presence of Unanticipated Classes

@article{Dalvi2016ConstrainedSL,
  title={Constrained Semi-supervised Learning in the Presence of Unanticipated Classes},
  author={Bhavana Bharat Dalvi},
  journal={SIGIR Forum},
  year={2016},
  volume={49},
  pages={147}
}
  • Bhavana Bharat Dalvi
  • Published 2016
  • Computer Science
  • SIGIR Forum
  • Traditional semi-supervised learning (SSL) techniques consider the missing labels of unlabeled datapoints as latent/unobserved variables, and model these variables, and the parameters of the model, using techniques like Expectation Maximization (EM). Such semisupervised learning techniques are widely used for Automatic Knowledge Base Construction (AKBC) tasks. We consider two extensions to traditional SSL methods which make it more suitable for a variety of AKBC tasks. First, we consider… CONTINUE READING
    2 Citations

    References

    SHOWING 1-2 OF 2 REFERENCES
    Exploratory learning. In Machine Learning and Knowledge Discovery in Databases, pages 128–143
    • 2013
    ERD'14: Entity Recognition and Disambiguation Challenge
    • 32
    • Highly Influential