M

Mlong T5 Tglobal Base Et Riigikogu Summary

Developed by rristo
This is an Estonian text summarization model based on the T5 architecture, specifically designed for summarizing stenographic records of the Estonian Parliament discussions.
Downloads 25
Release Time : 4/28/2024

Model Overview

The model is designed to process long text inputs (up to 2048 tokens) and generate summaries of Estonian parliamentary discussions. It is fine-tuned from the mlong-t5-tglobal-base model with an optimized vocabulary for Estonian language.

Model Features

Long text processing capability
Supports input sequences of up to 2048 tokens, suitable for processing lengthy parliamentary discussions
Estonian language optimization
Vocabulary has been pruned to retain only Estonian tokens present in the training data, improving efficiency
Specialized for parliamentary content
Specifically trained on Estonian parliamentary stenographic records, demonstrating superior performance in this domain

Model Capabilities

Text summarization
Long text processing
Estonian language understanding

Use Cases

Government document processing
Parliamentary discussion summarization
Automatically generates concise summaries of Estonian parliamentary discussions
ROUGE-1 score 36.1651, ROUGE-L score 28.339
Estonian text processing
General Estonian text summarization
Generates summaries for other Estonian texts
May provide reasonable accuracy to some extent
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase