Deep Multitask NLP Network

Closed weights NEC Laboratories 1.5M parameters July 2008

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
Organisation type
Industry
Country
United States of America
Published
5 July 2008
Authors
Ronan Collobert, Jason Weston

What it does

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

Domain
Language
Task
Language modeling
Approach
Unsupervised

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
1.5M

With a word vector size of 50 and a vocabulary size of 30,000, the embedding matrix has 1,500,000 parameters. There are also some small convolutional and dense layers with far fewer parameters.

Training data
633,000,000 tokens

Section 7: "631 million words from Wikipedia"

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
168 hours (7 days)

1 week on 1 computer

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,SOTA improvement
Record confidence
Speculative
Citations
7,095

Sources

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

Reference
A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning
Last updated
28 November 2025

What the numbers mean

Where it came from

Deep Multitask NLP Network was published by NEC Laboratories, in the country recorded as United States of America, during July 2008. The publishing organisation is categorised as industry.

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

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

What went into building it

It was trained on a corpus of about 633,000,000 tokens of text.

Its inclusion criterion: highly cited,SOTA improvement.

Answers

Deep Multitask NLP Network — common questions

01

Deep Multitask NLP Network— 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.

02

Deep Multitask NLP Network— how many parameters does it have?

It has a parameter count of 1.5M. With a word vector size of 50 and a vocabulary size of 30,000, the embedding matrix has 1,500,000 parameters. There are also some small convolutional and dense layers with far fewer parameters. 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.

03

Deep Multitask NLP Network— who created it?

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

04

Deep Multitask NLP Network— when was it released?

It was published in July 2008. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

Deep Multitask NLP Network— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

06

Deep Multitask NLP Network— 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.

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.