Reading List

The following list contains topics we intend to discuss in our seminars:

  1. Language Models as Knowledge Bases
  2. Pointer Networks
  3. Bidirectional LSTM-CRF models for sequence tagging
  4. Sequence level training with recurrent neural networks: this paper introduces the idea of using reinforcement learning to optimize non-differentiable metrics such as BLEU.
  5. Neural Architecture Search with Reinforcement Learning
  6. Linguistic Knowledge and Transferability of Contextual Representations