Tagging via Viterbi Decoding

Closed weights AT&T June 2002

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
AT&T
Organisation type
Industry
Country
United States of America
Published
1 June 2002
Authors
Michael Collins

What it does

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

Domain
Language
Task
Binary classification, Part-of-speech tagging

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
929,000 tokens

How it is classified

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

Record confidence
Unknown
Citations
2,582

Sources

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

Reference
Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms
Last updated
28 November 2025

What the numbers mean

Where it came from

Tagging via Viterbi Decoding was published by AT&T, in United States of America, in June 2002. It comes out of industry.

It works in Language, and is recorded as doing binary classification, Part-of-speech tagging.

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

Training and provenance

The training set ran to roughly 929,000 tokens.

Answers

Tagging via Viterbi Decoding — common questions

01

Is Tagging via Viterbi Decoding open source?

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

02

How many parameters does Tagging via Viterbi Decoding have?

No parameter count has been published for Tagging via Viterbi Decoding, which is why no memory or speed figure appears on this page.

03

Who created Tagging via Viterbi Decoding?

Tagging via Viterbi Decoding was published by AT&T, based in United States of America, categorised as industry.

04

When was Tagging via Viterbi Decoding released?

Tagging via Viterbi Decoding was published in June 2002. 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

What is Tagging via Viterbi Decoding used for?

Tagging via Viterbi Decoding works in Language, and is recorded as handling binary classification, Part-of-speech tagging. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

06

What GPU do I need to run Tagging via Viterbi Decoding?

None. Tagging via Viterbi Decoding 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.