FANDOM


Word-level:

  • AWD LSTM (Merity et al. 2017)[1] --> used in UMFiT (Howard and Ruder, 2018)[2]
  • Deepmoji (Felbo et al., 2017)[3]

Character-level:

References Edit

  1. Merity, S., Keskar, N. S., & Socher, R. (2015). Regularizing and Optimizing LSTM Language Models.
  2. Howard, J., & Ruder, S. (2018). Universal Language Model Fine-tuning for Text Classification.
  3. Felbo, B., Mislove, A., Rahwan, I., Lehmann, S., & Science, I. (2017). Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm.