@InProceedings{bizzoni-chatzikyriakidis-ghanimifard:2017:StyVa,
  author    = {Bizzoni, Yuri  and  Chatzikyriakidis, Stergios  and  Ghanimifard, Mehdi},
  title     = {"Deep" Learning : Detecting Metaphoricity in Adjective-Noun Pairs},
  booktitle = {Proceedings of the Workshop on Stylistic Variation},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {43--52},
  abstract  = {Metaphor is one of the most studied and widespread figures of speech and an
	essen- tial element of individual style. In this pa- per we look at metaphor
	identification in Adjective-Noun pairs. We show that us- ing a single neural
	network combined with pre-trained vector embeddings can outper- form the state
	of the art in terms of accu- racy. In specific, the approach presented in this
	paper is based on two ideas: a) trans- fer learning via using pre-trained
	vectors representing adjective noun pairs, and b) a neural network as a model
	of composition that predicts a metaphoricity score as out- put. We present
	several different architec- tures for our system and evaluate their per-
	formances. Variations on dataset size and on the kinds of embeddings are also
	inves- tigated. We show considerable improve- ment over the previous approaches
	both in terms of accuracy and w.r.t the size of an- notated training data.},
  url       = {http://www.aclweb.org/anthology/W17-4906}
}