The Optimal Information Retrieval Based on SVM

@inproceedings{Sun2013TheOI,
  title={The Optimal Information Retrieval Based on SVM},
  author={Jianming Sun and Qingli Sun},
  year={2013}
}
A new sentence level kernel function based on string sequence kernel function and word sequence function is proposed in this paper. Also two feasible algorithms-sentence collection kernel function and sentence sequence kernel function are put forward. These two kernel functions are based on sentence level and sequence kernel function. Pre-treatment text database is treated by practicing the SVM method. The classification and discrimination function of different text can be drawn. The resource… CONTINUE READING

Figures and Topics from this paper.

Explore Further: Topics Discussed in This Paper

References

Publications referenced by this paper.
SHOWING 1-10 OF 14 REFERENCES

Chang.,PSVM: Parallelizing Support Vector Machines on Distributed Computers. Foundations of Large-Scale Multimedia Information Management

  • Y. Edward
  • 2011

Feature Selection for Classification of Hyperspectral Data by SVM

Margin-based feature selection for hyperspectral data

  • Mahesh Pal
  • Computer Science, Geography
  • Int. J. Appl. Earth Obs. Geoinformation
  • 2009

de Andrs , Gene selection and classification of microarray data using random forest

  • R. Daz-Uriarte, A. S.
  • BMC Bioinf .
  • 2009

Lin A comparison of methods for multi - class support vector machines

  • C.-J.
  • IEEE Trans . Neural Netw .
  • 2006

A semilabeledsampledriven bagging technique for illposed classification problems , IEEE Geosci

  • L. Bruzzone
  • Remote Sens . Lett .
  • 2005