@InProceedings{skurniak-janicka-wawer:2018:W18-09,
  author    = {Skurniak, Filip  and  Janicka, Maria  and  Wawer, Aleksander},
  title     = {Multi-Module Recurrent Neural Networks with Transfer Learning},
  booktitle = {Proceedings of the Workshop on Figurative Language Processing},
  month     = {June},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {128--132},
  abstract  = {This paper describes multiple solutions designed and tested for the problem of word-level metaphor detection. The proposed systems are all based on variants of recurrent neural network architectures. Specifically, we explore multiple sources of information: pre-trained word embeddings (Glove), a dictionary of language concreteness and a transfer learning scenario based on the states of an encoder network from neural network machine translation system. One of the architectures is based on combining all three systems: (1) Neural CRF (Conditional Random Fields), trained directly on the metaphor data set; (2) Neural Machine Translation encoder of a transfer learning scenario; (3) a neural network used to predict final labels, trained directly on the metaphor data set. Our results vary between test sets: Neural CRF standalone is the best one on submission data, while combined system scores the highest on a test subset randomly selected from training data.},
  url       = {http://www.aclweb.org/anthology/W18-0917}
}