@InProceedings{croce-EtAl:2017:Long,
  author    = {Croce, Danilo  and  Filice, Simone  and  Castellucci, Giuseppe  and  Basili, Roberto},
  title     = {Deep Learning in Semantic Kernel Spaces},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {345--354},
  abstract  = {Kernel methods enable the direct usage of structured representations of textual
	data during language learning and inference tasks. Expressive kernels, such as
	Tree Kernels, achieve excellent performance in NLP. 
	On the other side, deep neural networks have been demonstrated effective in
	automatically learning feature representations during training. However, their
	input is tensor data, i.e., they can not manage rich structured information.
	In this paper, we show that expressive kernels and deep neural networks can be
	combined in a common framework in order to (i) explicitly model structured
	information and (ii) learn non-linear decision functions. We show that the
	input layer of a deep architecture can be pre-trained through the application
	of the Nystrom low-rank approximation of kernel spaces. 
	The resulting ``kernelized" neural network achieves state-of-the-art accuracy
	in three different tasks.},
  url       = {http://aclweb.org/anthology/P17-1032}
}