@InProceedings{schwartz-thomson-smith:2018:Long,
  author    = {Schwartz, Roy  and  Thomson, Sam  and  Smith, Noah A.},
  title     = {Bridging CNNs, RNNs, and Weighted Finite-State Machines},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {295--305},
  abstract  = {Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances. In this paper we present SoPa, a new model that aims to bridge these two approaches. SoPa combines neural representation learning with weighted finite-state automata (WFSAs) to learn a soft version of traditional surface patterns. We show that SoPa is an extension of a one-layer CNN, and that such CNNs are equivalent to a restricted version of SoPa, and accordingly, to a restricted form of WFSA. Empirically, on three text classification tasks, SoPa is comparable or better than both a BiLSTM (RNN) baseline and a CNN baseline, and is particularly useful in small data settings.},
  url       = {http://www.aclweb.org/anthology/P18-1028}
}