Meta-Learning a Dynamical Language ModelDownload PDF

Feb 12, 2018 (edited Jun 04, 2018)ICLR 2018 Workshop SubmissionReaders: Everyone
  • Keywords: language models, hierarchical representations, meta-learning, nonstationarity, catastrophic forgetting, recurrent neural network
  • TL;DR: Language modeling with dynamical weights as an instance of continuous meta-learning
  • Abstract: We consider the task of word-level language modeling and study the possibility of combining hidden-states-based short-term representations with medium-term representations encoded in dynamical weights of a language model. Our work extends recent experiments on language models with dynamically evolving weights by casting the language modeling problem into an online learning-to-learn framework in which a meta-learner is trained by gradient-descent to continuously update a language model weights.
4 Replies