Label Embedding Approach for Transfer Learning

@inproceedings{Obeidat2016LabelEA,
  title={Label Embedding Approach for Transfer Learning},
  author={Rasha Obeidat and Xiaoli Z. Fern and Prasad Tadepalli},
  booktitle={ICBO/BioCreative},
  year={2016}
}
Automatically tagging textual mentions with the concepts, types and entities that they represent are important tasks for which supervised learning has been found to be very effective. In this paper, we consider the problem of exploiting multiple sources of training data with variant ontologies. We present a new transfer learning approach based on embedding multiple label sets in a shared space, and using it to augment the training data. Keywords— transfer learning, Label embedding. 

From This Paper

Figures, tables, and topics from this paper.
1 Citations
11 References
Similar Papers

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 11 references

Relations between two sets of variates

  • H. Hotelling
  • Biometrika, vol. 28, no. 3/4, pp. 321–377, 1936.
  • 1936
Highly Influential
5 Excerpts

Sch ̈olkopf, “An empirical analysis of domain adaptation algorithms for genomic sequence analysis,”in

  • G. Schweikert, G. R ̈atsch, C. Widmer
  • Advances in Neural Information Processing Systems…
  • 2009

Similar Papers

Loading similar papers…