Sequence-to-Sequence Model

• Also seq2seq, Encoder-Decoder, and Sequence transformation model.

• 1409.3215 Sequence to Sequence Learning with Neural Networks(2014)

  • If we use the self-caution mechanism, isn’t there much need to use the Encoder-Decoder configuration? I’m starting to get the feeling that it is (2018-10-17)

• Pointer Networks

  • 1506.03134 Pointer Networks(2015)
  • It is possible to use the pointer to copy from the input
  • CopyNet
    • 1603.06393 Incorporating Copying Mechanism in Sequence-to-Sequence Learning
  • Pointer Sentinel Mixture Models
    • 1609.07843 Pointer Sentinel Mixture Models
  • Pointer-Generator Network (2017)
    • 1704.04368 Get To The Point: Summarization with Pointer-Generator Networks https://qiita.com/ymym3412/items/c84e6254de89c9952c55

---

This page is auto-translated from /nishio/Sequence-to-Sequenceモデル using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.