character-aware neural language models

Yoon Kim, Yacine Jernite, David Sontag, Alexander M. Rush

We describe a simple neural language model that relies only on character-level inputs. Predictions are still made at the word-level. Our model employs a convolutional neural network (CNN) over characters, whose output is given to a long short-term memory (LSTM) recurrent neural network language model (RNN-LM). On the English Penn Treebank the model is on par with the existing state-of-the-art despite having 60% fewer parameters. On languages with rich morphology (Czech, German, French, Spanish, Russian), the model consistently outperforms a Kneser-Ney baseline (by 30-35%) and a word-level LSTM baseline (by 15-25%), again with far fewer parameters. Our results suggest that on many languages, character inputs are sufficient for language modeling.

Suggested to Venues

Discussion