The Transformer: attention-based sequence modelling

What changed

Sequence transduction gained an attention-based architecture with greater parallelism than recurrent designs.

Scientific scope

The human-designed attention-based encoder–decoder and the experiments in version 5 of the 2017 paper.

Evidence

The cited historical record or published author account supports this scoped contribution. The source-reading boundary is stated at each link; a WRS grade is not an independent scientific validation.

Contributors

• The eight named paper authors · SCIENCE: Architecture and experiments; equal contribution stated by the paper, full byline retained in the record.

• Attention Is All You Need, v5

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