Identifying Chemical-Disease Relationship in Biomedical Text Using a Multiple Kernel Learning-Boosting Method.

Journal: Studies in health technology and informatics
Published Date: Jan 1, 2017

Abstract

Chemical-induced disease relations (CID) are crucial in various biomedical tasks. In the CID task of Biocreative V, no classifiers with multiple kernels have been developed. In this study, a multiple kernel learning-boosting (MKLB) method is proposed. Different kernel functions according to different types of features were constucted and boosted, each of which were learned with multiple kernels. Our multiple kernel learning-boosting (MKLB) method achieved a F1 score of 0.5068 without incorporating knowledge bases.

Authors

  • Yueping Sun
    Institute of Medical Information & Library, Chinese Academy of Medical Sciences, Beijing, China.
  • Yu Zhang
    College of Marine Electrical Engineering, Dalian Maritime University, Dalian, China.
  • Jiao Li
    CAS Key Laboratory of Tropical Marine Bio-resources and Ecology, South China Sea Institute of Oceanology, Chinese Academy of Sciences Guangzhou 510301 China yinhao@scsio.ac.cn.

Keywords

External Resources

Popular Topics
Recent Journals