LINEAiGE
AI HISTORY

Sequence to Sequence Learning with Neural Networks

Ilya Sutskever, Oriol Vinyals, and Quoc V. Le submitted 'Sequence to Sequence Learning with Neural Networks' on September 10, 2014, presenting an end-to-end sequence-learning approach that uses one multilayer LSTM to encode an input sequence into a fixed-dimensional vector and another deep LSTM to decode the target sequence.

10 September 2014AI HISTORYVERIFIED

Historical classification

This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.

Why it matters

A documented neural sequence-modeling research milestone demonstrating an end-to-end encoder-decoder approach for variable-length sequence mapping, evaluated on English-to-French machine translation.

People, organizations & technologies

PEOPLE
Ilya Sutskever, Oriol Vinyals, Quoc V. Le

TECHNOLOGIES
Sequence-to-sequence learning, LSTM, Encoder-decoder

Evidence & verification

STATE
verified

CONFIDENCE
high

LAST VERIFIED
2026-09-10T03:05:17+08:00

The original arXiv record establishes the September 10, 2014 first-submission date, authors, and the end-to-end sequence-learning method using a multilayer LSTM encoder and deep LSTM decoder. The official NeurIPS 2014 proceedings independently corroborate the title, authors, conference placement, and technical description. This record uses the arXiv submission date strictly as a research-publication milestone. It does not claim this date as the invention of all encoder-decoder methods, a software/product release, deployment date, or causal ancestor of later systems. No geography, affiliation, ancestry, influence, causality, or relationships are inferred.

Sources

SOURCE 1 · PRIMARY · CLAIM-EVIDENCE

Sequence to Sequence Learning with Neural Networks

arXiv

PUBLISHED
2014-09-10

SOURCE 2 · PRIMARY · CORROBORATION

Sequence to Sequence Learning with Neural Networks

NeurIPS

Trace the chronology

Record identity

LINEAiGE ID
seq2seq-2014