Joint Probability Machine Translation

Closed weights University of Southern California 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
University of Southern California
Organisation type
Academia
Country
United States of America
Published
1 June 2002
Authors
Daniel Marcu, William Wong

What it does

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

Domain
Language
Task
Translation

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
100,000 tokens

[WORDS] "To evaluate our system, we trained [...] our joint probability model on a French-English parallel corpus of 100,000 sentence pairs from the Hansard corpus. The sentences in the corpus were at most 20 words long. The English side had a total of 1,073,480 words (21,484 unique tokens). The French side had a total of 1,177,143 words (28,132 unique tokens)"

How it is classified

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

Citations
623

Sources

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

Reference
A Phrase-Based, Joint Probability Model for Statistical Machine Translation
Last updated
28 November 2025

What the numbers mean

What this model is

Joint Probability Machine Translation was published by University of Southern California, in United States of America, in June 2002. academia is the category the publisher falls under.

It works in Language, and is recorded as doing translation.

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

How it was trained

It was trained on about 100,000 tokens of text.

Answers

Joint Probability Machine Translation — common questions

01

What GPU do I need to run Joint Probability Machine Translation?

None. Joint Probability Machine Translation 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

Is Joint Probability Machine Translation open source?

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

03

How many parameters does Joint Probability Machine Translation have?

No parameter count has been published for Joint Probability Machine Translation, which is why no memory or speed figure appears on this page.

04

Who created Joint Probability Machine Translation?

Joint Probability Machine Translation was published by University of Southern California, based in United States of America, categorised as academia.

05

When was Joint Probability Machine Translation released?

Joint Probability Machine Translation 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.

06

What is Joint Probability Machine Translation used for?

Joint Probability Machine Translation works in Language, and is recorded as handling translation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

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.