Data provided by National Institute of Standards and Technology
TOVA is a topic modeling platform with a plug-in architecture, supporting training and inference via CLI and web interface.
TOVA is a highly extensible topic modeling platform that supports both traditional and LLM-based models through a unified CLI and interactive web interface. It provides a comprehensive end-to-end workflow, allowing users to train models with full hyperparameter control, enrich topics with LLM-generated labels, and evaluate results using an interactive dashboard rich with visualizations and metrics. Additionally, TOVA offers robust features for running inference on new documents, built-in uncertainty quantification to estimate document-topic probabilities, and a flexible plug-in architecture that makes it easy to integrate new model classes.
About this Dataset
Updated: 2026-09-04
Metadata Last Updated:
2026-06-10 00:00:00
Date Created:
N/A
Data Provided by:
Dataset Owner:
N/A
| Title | TOVA: Topic Visualization & Analysis |
|---|---|
| Description | TOVA is a topic modeling platform with a plug-in architecture, supporting training and inference via CLI and web interface. TOVA is a highly extensible topic modeling platform that supports both traditional and LLM-based models through a unified CLI and interactive web interface. It provides a comprehensive end-to-end workflow, allowing users to train models with full hyperparameter control, enrich topics with LLM-generated labels, and evaluate results using an interactive dashboard rich with visualizations and metrics. Additionally, TOVA offers robust features for running inference on new documents, built-in uncertainty quantification to estimate document-topic probabilities, and a flexible plug-in architecture that makes it easy to integrate new model classes. |
| Modified | 2026-06-10 00:00:00 |
| Publisher Name | National Institute of Standards and Technology |
| Contact | mailto:[email protected] |
| Keywords | natural language processing , topic model , artificial intelligence , large language model , content analysis , grounded theory , unstructured text |
{
"identifier": "ark:\/88434\/mds2-4134",
"accessLevel": "public",
"contactPoint": {
"hasEmail": "mailto:[email protected]",
"fn": "Juan Fung"
},
"programCode": [
"006:045"
],
"landingPage": "https:\/\/data.nist.gov\/od\/id\/mds2-4134",
"title": "TOVA: Topic Visualization & Analysis",
"description": "TOVA is a topic modeling platform with a plug-in architecture, supporting training and inference via CLI and web interface.\n\nTOVA is a highly extensible topic modeling platform that supports both traditional and LLM-based models through a unified CLI and interactive web interface. It provides a comprehensive end-to-end workflow, allowing users to train models with full hyperparameter control, enrich topics with LLM-generated labels, and evaluate results using an interactive dashboard rich with visualizations and metrics. Additionally, TOVA offers robust features for running inference on new documents, built-in uncertainty quantification to estimate document-topic probabilities, and a flexible plug-in architecture that makes it easy to integrate new model classes.",
"language": [
"en"
],
"distribution": [
{
"accessURL": "https:\/\/github.com\/usnistgov\/TOVA",
"format": "code repo",
"description": "NIST GitHub repository for TOVA",
"title": "TOVA.git"
},
{
"downloadURL": "https:\/\/data.nist.gov\/od\/ds\/mds2-4134\/readme.md",
"format": "markdown",
"description": "Describes purpose of TOVA, functionality, setup and configuration, and troubleshooting",
"mediaType": "text\/markdown",
"title": "README"
}
],
"bureauCode": [
"006:55"
],
"modified": "2026-06-10 00:00:00",
"publisher": {
"@type": "org:Organization",
"name": "National Institute of Standards and Technology"
},
"theme": [
"Information Technology:Computational science",
"Information Technology:Software research"
],
"keyword": [
"natural language processing",
"topic model",
"artificial intelligence",
"large language model",
"content analysis",
"grounded theory",
"unstructured text"
]
}
