Designing a Better Data Representation for Deep Neural Networks and Text Classification

@article{Prusa2016DesigningAB,
  title={Designing a Better Data Representation for Deep Neural Networks and Text Classification},
  author={Joseph D. Prusa and Taghi M. Khoshgoftaar},
  journal={2016 IEEE 17th International Conference on Information Reuse and Integration (IRI)},
  year={2016},
  pages={411-416}
}
Traditional machine learning requires data to be described by attributes prior to applying a learning algorithm. In text classification tasks, many feature engineering methodologies have been proposed to extract meaningful features, however, no best practice approach has emerged. Traditional methods of feature engineering have inherent limitations due to loss of information and the limits of human design. An alternative is to use deep learning to automatically learn features from raw text data… CONTINUE READING
4 Citations
18 References
Similar Papers

Citations

Publications citing this paper.

References

Publications referenced by this paper.

Similar Papers

Loading similar papers…