Bengio and colleagues: a neural probabilistic language model

What changed

Jointly learned distributed word embeddings and neural sequence probabilities with reported corpus gains.

Scientific scope

The record is the exact four-author 2003 JMLR paper. Results remain bounded to the architectures, datasets and comparisons reported, and the work does not absorb word2vec, recurrent language models, transformers or modern foundation models.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact four-author 2003 JMLR paper. Results remain bounded to the architectures, datasets and comparisons reported, and the work does not absorb word2vec, recurrent language models, transformers or modern foundation models.

Contributors

• Yoshua Bengio · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Réjean Ducharme · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Pascal Vincent · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Christian Jauvin · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• JMLR full text of neural probabilistic language model
• Yoshua Bengio publication page for neural language model

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