Automated WSD via WordNet

Closed weights University of Sussex July 2004

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 Sussex
Organisation type
Academia
Country
United Kingdom of Great Britain and Northern Ireland
Published
1 July 2004
Authors
D McCarthy, R Koeling, J Weeds

What it does

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

Domain
Language
Task
Word sense disambiguation

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
tokens

They do two experiments, one on a dataset of 5.000 tagged words and another one on two datasets containing a total of around 40 million words, of which they only select 38 unique words and manually annotate the senses? I think the first one is more representative

How it is classified

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

Citations
475

Sources

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

Reference
Finding Predominant Word Senses in Untagged Text
Last updated
28 November 2025

What the numbers mean

About this model

Automated WSD via WordNet was published by University of Sussex, in United Kingdom of Great Britain and Northern Ireland, in July 2004. It comes out of academia.

It works in Language, and is recorded as doing word sense disambiguation.

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

Answers

Automated WSD via WordNet — common questions

01

How many parameters does Automated WSD via WordNet have?

No parameter count has been published for Automated WSD via WordNet, which is why no memory or speed figure appears on this page.

02

Who created Automated WSD via WordNet?

Automated WSD via WordNet was published by University of Sussex, based in United Kingdom of Great Britain and Northern Ireland, categorised as academia.

03

When was Automated WSD via WordNet released?

Automated WSD via WordNet was published in July 2004. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is Automated WSD via WordNet used for?

Automated WSD via WordNet works in Language, and is recorded as handling word sense disambiguation. 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.

05

What GPU do I need to run Automated WSD via WordNet?

None. Automated WSD via WordNet 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.

06

Is Automated WSD via WordNet open source?

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

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.