Section outline

  • May 29th, Friday (10:30-12:30)

    Machine translation

    • RNN: training algorithm and teacher forcing
    • RNN: attention and dynamic context vector
    • RNN: dot-product attention
    • RNN: bilinear attention
    • Transformer-based architecture
    • Cross-attention, query, key and value
    • Search tree and beam search
    • Parallel corpora
    • Evaluation: BLEU and METEOR

    References

    • Jurafsky and Martin, chapter 12