Word Representations

Closed weights University of Montreal / Université de Montréal,University of Illinois Urbana-Champaign (UIUC) June 2010

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
University of Montreal / Université de Montréal,University of Illinois Urbana-Champaign (UIUC)
Organisation type
Academia,Academia
Country
Canada, United States of America
Published
1 June 2010
Authors
Joseph Turian, Lev-Arie Ratinov, Yoshua Bengio

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.

Training data
37,000,000 tokens

Section 6: "After cleaning, there are 37 million words (58% of the original) in 1.3 million sentences"

How it is classified

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

Citations
2,510

Sources

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

Reference
Word Representations: A Simple and General Method for Semi-Supervised Learning
Last updated
28 November 2025

What the numbers mean

About this model

Word Representations was published by University of Montreal / Université de Montréal,University of Illinois Urbana-Champaign (UIUC), in Canada, in June 2010. academia,Academia is the category the publisher falls under.

It works in Language, and is recorded as doing language Structure Modeling.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

Around 37,000,000 tokens went into training it.

Answers

Word Representations — common questions

01

When was Word Representations released?

Word Representations was published in June 2010. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

What is Word Representations used for?

Word Representations works in Language, and is recorded as handling language Structure Modeling. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

What GPU do I need to run Word Representations?

None. Word Representations 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.

04

Is Word Representations open source?

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

05

How many parameters does Word Representations have?

No parameter count has been published for Word Representations, which is why no memory or speed figure appears on this page.

06

Who created Word Representations?

Word Representations was published by University of Montreal / Université de Montréal,University of Illinois Urbana-Champaign (UIUC), based in Canada, categorised as academia,Academia.

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.