Language, speech & LLMs· 2003
A Neural Probabilistic Language Model
On the reading lists
- #146 in the Top 500 (2026 edition)
- #23 in Language, speech & LLMs (2026 edition)
Why it matters
Pioneered jointly learned distributed word representations and neural language modeling.
Condensed from the expert lists' notes.
Reading it
Difficulty: Intermediate
Read this first: neural network basics (backpropagation); n-gram language models.
The record
- First released
- 2003 (from OpenAlex)
- Citations
- 8,212 citations, as counted by
Semantic Scholar (non-commercial licence) - Named by
- both expert lists
- Also relevant to
- Computer vision & multimodal
- Score
- 0.603 · computed rank 146 · consensus 0.78, must-read 1, citations percentile 0.769 (2000s · language), awards 0, existing lists 0. Method
Editor's notes
- Readability check: pass: The first neural language model with learned word embeddings. (AI draft (Claude), not yet reviewed, 2026-10-29)
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0), and
Semantic Scholar (used under its non-commercial API licence). Each count names its source. See the method.