Semantic Taxonomy Induction

Closed weights Stanford University 0.1K parameters July 2006

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
Stanford University
Organisation type
Academia
Country
United States of America
Published
7 July 2006
Authors
Rion Snow, Dan Jurafsky, and Andrew Y. Ng

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.

Parameters
0.1K

The main learning algorithm is a logistic classifier. The input is a matrix M, where the rows are pairs of words, and the columns (variables) are counts of occurrences of synthetic dependency paths between those two words. Since there are on the order of 10~100 different types of syntactic relationships, this is the number of length-1 paths, and thus the number of parameters if only length-1 paths are used. However, if the length of the paths considered is longer (say, 5), then the parameters …

Training data
tokens

[Classification task] The labeled training set is constructed by labeling the collected feature vectors as positive “known hypernym” or negative “known non-hypernym” examples using WordNet 2.0; 49,922 feature vectors were labeled as positive training examples, and 800,828 noun pairs were labeled as negative training examples. 800,828 + 49,922 = 850750

How it is classified

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

Citations
571

Sources

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

Reference
Semantic Taxonomy Induction from Heterogenous Evidence
Last updated
28 November 2025

What the numbers mean

What this model is

Semantic Taxonomy Induction was published by Stanford University, in United States of America, in July 2006. 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.

Answers

Semantic Taxonomy Induction — common questions

01

What is Semantic Taxonomy Induction used for?

Semantic Taxonomy Induction 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.

02

What GPU do I need to run Semantic Taxonomy Induction?

None. Semantic Taxonomy Induction 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.

03

Is Semantic Taxonomy Induction open source?

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

04

How many parameters does Semantic Taxonomy Induction have?

Semantic Taxonomy Induction has 0.1K parameters. The main learning algorithm is a logistic classifier. The input is a matrix M, where the rows are pairs of words, and the columns (variables) are counts of occurrences of synthetic dependency paths between those two words. Since there are on the order of 10~100 different types of syntactic relationships, this is the number of length-1 paths, and thus the number of parameters if only length-1 paths are used. However, if the length of the paths considered is longer (say, 5), then the parameters would be on the order of (10~100)^5. It's not clear to me which is the case. 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.

05

Who created Semantic Taxonomy Induction?

Semantic Taxonomy Induction was published by Stanford University, based in United States of America, categorised as academia.

06

When was Semantic Taxonomy Induction released?

Semantic Taxonomy Induction was published in July 2006. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

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.