Post-Cutoff.com
  1. Home
  2. Timeline
  3. 2014
  4. Sequence-to-sequence learning and neural attention

Sequence-to-sequence learning and neural attention

★★★★researchGoogleUniversité de Montréalconfidence: high

Sutskever, Vinyals and Le's seq2seq (LSTM encoder–decoder) and Bahdanau, Cho and Bengio's attention mechanism, both posted in September 2014, made end-to-end neural machine translation work.

Key facts

What happened

Two papers showed neural networks could map whole sequences to sequences, and that letting the decoder 'attend' to encoder states greatly improved long sentences.

Why it matters

Established the encoder–decoder paradigm and attention — the direct precursors of the Transformer and modern LLMs.

Changelog

  • 2026-09-29: created

Related events

  1. Hochreiter & Schmidhuber introduce Long Short-Term Memory (LSTM) ★★★★
  2. 'Attention Is All You Need' introduces the Transformer ★★★★★

Sources (3)

id: 2014-09-10-seq2seq-attention · updated 2026-09-29 · open in the interactive timeline