NLP from scratch

Closed weights NEC Laboratories,Princeton University 5M parameters November 2011

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
NEC Laboratories,Princeton University
Organisation type
Industry,Academia
Country
United States of America
Published
8 November 2011
Authors
Ronan Collobert, J. Weston, L. Bottou, Michael Karlen, K. Kavukcuoglu, P. Kuksa

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Language Structure Modeling

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
5M

"The capacity of our network architectures lies mainly in the word lookup table, which contains 50 × 100,000 parameters to train. [...] most of the trainable parameters are located in the lookup tables."

Training data
852,000,000 tokens

"Section 4 leverages large unlabeled data sets (∼ 852 million words)"

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Wall-clock time
72 hours

"Chunking and NER take about one hour to train, POS takes few hours, and SRL takes about three days." SRL is the longest task.

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
Highly cited
Citations
7,640

Sources

Where this record came from and when it was last checked.

Reference
Natural Language Processing (Almost) from Scratch
Last updated
28 November 2025

What the numbers mean

Where it came from

NLP from scratch was published by NEC Laboratories,Princeton University, in the country recorded as United States of America, during November 2011. It comes out of an organisation categorised as industry,Academia.

It works in the domain of Language, and is recorded as performing the task of language Structure Modeling.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

Training consumed a corpus of around 852,000,000 tokens of text.

Its inclusion criterion: highly cited.

Answers

NLP from scratch — common questions

01

NLP from scratch— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

02

NLP from scratch— is it open source?

The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

03

NLP from scratch— how many parameters does it have?

It has a parameter count of 5M. "The capacity of our network architectures lies mainly in the word lookup table, which contains 50 × 100,000 parameters to train. [...] most of the trainable parameters are located in the lookup tables.". That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

04

NLP from scratch— who created it?

It was published by NEC Laboratories,Princeton University, based in United States of America, an organisation categorised as industry,Academia.

05

NLP from scratch— when was it released?

It was published in November 2011. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

NLP from scratch— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language Structure Modeling. These are the areas it was designed around; they describe intent rather than a hard boundary.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.