@InProceedings{hiebert-EtAl:2018:BlackboxNLP,
  author    = {Hiebert, Avery  and  Peterson, Cole  and  Fyshe, Alona  and  Mehta, Nishant},
  title     = {Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models},
  booktitle = {Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP},
  month     = {November},
  year      = {2018},
  address   = {Brussels, Belgium},
  publisher = {Association for Computational Linguistics},
  pages     = {258--266},
  abstract  = {While Long Short-Term Memory networks (LSTMs) and other forms of recurrent neural network have been successfully applied to language modeling on a character level, the hidden state dynamics of these models can be difficult to interpret. We investigate the hidden states of such a model by using the HDBSCAN clustering algorithm to identify points in the text at which the hidden state is similar. Focusing on whitespace characters prior to the beginning of a word reveals interpretable clusters that offer insight into how the LSTM may combine contextual and character-level information to identify parts of speech. We also introduce a method for deriving word vectors from the hidden state representation in order to investigate the word-level knowledge of the model. These word vectors encode meaningful semantic information even for words that appear only once in the training text.},
  url       = {http://www.aclweb.org/anthology/W18-5428}
}