mT5-base-HunSum-2 Open-source Model - Free Support for Rapid Generation of Hungarian Text Summaries

Mt5 Base HunSum 2

Developed by SZTAKI-HLT

Hungarian abstract summarization model based on mT5-base, trained with HunSum-2 dataset

OtherOpen Source License:Apache-2.0 #Hungarian abstract summarization #Multilingual MT5 architecture #High ROUGE-1 accuracy

Downloads 52

Release Time : 4/3/2024

Model Overview

This model is specifically designed for Hungarian text summarization tasks, capable of extracting key information from Hungarian texts to generate concise summaries.

Model Features

Hungarian language optimization

Specially trained and optimized for Hungarian texts

Abstractive summarization

Capable of generating fluent and natural summary texts, not just extractive summaries

Optimized inference parameters

Uses strategies like beam search and length penalty to improve generation quality

Model Capabilities

Hungarian text comprehension

Abstractive summarization

Long text compression

Use Cases

News media

News summarization

Automatically generates brief summaries for Hungarian news articles

ROUGE-1 score 40.06

Document processing

Report summarization

Generates executive summaries for Hungarian business reports or research documents

Property	Details
Model Type	Text Summarization
Language(s) (NLP)	Hungarian
Resource(s) for more information	GitHub Repo

Property	Details
Batch Size	12
Learning Rate	5e-5
Weight Decay	0.01
Warmup Steps	3000
Epochs	10
no_repeat_ngram_size	3
num_beams	5
early_stopping	False
encoder_no_repeat_ngram_size	4

Metric	Value
ROUGE-1	40.06
ROUGE-2	12.67
ROUGE-L	25.93

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Mt5 Base HunSum 2

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 mT5-base-HunSum-2

🚀 Quick Start

✨ Features

Intended uses & limitations

Parameters

Results

📄 License