Sutskever, Vinyals and Le: sequence-to-sequence learning

What changed

An end-to-end recurrent system showed competitive variable-length translation performance.

Scientific scope

Three-author 2014 paper; not attention, Transformers or all production translation systems.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. This is the exact 2014 three-author encoder-decoder paper. Attention, Transformers and later production translation systems are separate contributions.

Contributors

• Ilya Sutskever · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Oriol Vinyals · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Quoc V. Le · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• Sutskever, Vinyals and Le, Sequence to Sequence Learning with Neural Networks
• Google Research: Sequence to Sequence Learning with Neural Networks

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction