@InProceedings{baker-korhonen-pyysalo:2016:BioTxtM2016,
  author    = {Baker, Simon  and  Korhonen, Anna  and  Pyysalo, Sampo},
  title     = {Cancer Hallmark Text Classification Using Convolutional Neural Networks},
  booktitle = {Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {1--9},
  abstract  = {Methods based on deep learning approaches have recently achieved
	state-of-the-art performance in a range of machine learning tasks and are
	increasingly applied to natural language processing (NLP). Despite strong
	results in various established NLP tasks involving general domain texts, there
	is only limited work applying these models to biomedical NLP. In this paper, we
	consider a Convolutional Neural Network (CNN) approach to biomedical text
	classification. Evaluation using a recently introduced cancer domain dataset
	involving the categorization of documents according to the well-established
	hallmarks of cancer shows that a basic CNN model can achieve a level of
	performance competitive with a Support Vector Machine (SVM) trained using
	complex manually engineered features optimized to the task. We further show
	that simple modifications to the CNN hyperparameters, initialization, and
	training process allow the model to notably outperform the SVM, establishing a
	new state of the art result at this task. We make all of the resources and
	tools introduced in this study available under open licenses from
	https://cambridgeltl.github.io/cancer-hallmark-cnn/ .},
  url       = {http://aclweb.org/anthology/W16-5101}
}