/Stanford-CS224n-20winter

Homework of Natural Language Processing with Deep Learning(CS224n) @ Stanford.

Primary LanguageJavaScript

CS224n Natural Language Processing with Deep Learning @ Stanford

Assignment 1

  • visualization of word vector
    • naive co-occurrence matrix
    • GloVe
  • analogy exercise

Assignment 2

  • Word2vec (Skip Gram)
  • naive softmax
  • negative sampling
  • Dataset: Stanford Sentiment Treebank

Assignment 3

  • Dependence parsing using fully connected network
  • Data preprocessing: build single-step decision according to parsing tree GT

Assignment 4

  • NMT with attention: pad all after the <END> token
  • beam search
  • BLEU calculation

Assignment 5

  • Mostly based on Assignment 4
  • Attention NMT with both word-level and character-level CNN and LSTM
  • Character-level CNN word embedding module for all inputs words
  • character-level RNN decoder for all output words using greedy decoding