@InProceedings{baker-korhonen:2017:BioNLP17,
  author    = {Baker, Simon  and  Korhonen, Anna},
  title     = {Initializing neural networks for hierarchical multi-label text classification},
  booktitle = {BioNLP 2017},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada,},
  publisher = {Association for Computational Linguistics},
  pages     = {307--315},
  abstract  = {Many tasks in the biomedical domain require the assignment of one or more
	predefined labels to input text, where the labels are a part of a hierarchical
	structure (such as a taxonomy). The conventional approach is to use a
	one-vs.-rest (OVR) classification setup, where a binary classifier is trained
	for each label in the taxonomy or ontology where all instances not belonging to
	the class are considered negative examples. The main drawbacks to this approach
	are that dependencies between classes are not leveraged in the training and
	classification process, and the additional computational cost of training
	parallel classifiers. In this paper, we apply a new method for hierarchical
	multi-label text classification that initializes a neural network model final
	hidden layer such that it leverages label co-occurrence relations such as
	hypernymy. This approach elegantly lends itself to hierarchical classification.
	We evaluated this approach using two hierarchical multi-label text
	classification tasks in the biomedical domain using both sentence- and
	document-level classification. Our evaluation shows promising results for this
	approach.},
  url       = {http://www.aclweb.org/anthology/W17-2339}
}