Meeting Summary - Samsum Open-Source Dialogue Summarization Model - Free Deployment for Precise Generation of Dialogue Summaries

Meeting Summary Samsum

Developed by knkarthick

This model is a seq2seq model based on the BART architecture, specifically designed for dialogue summarization tasks, fine-tuned on the SAMSum dataset.

Text Generation

Transformers

EnglishOpen Source License:Apache-2.0 #Dialogue Summarization #High ROUGE Scores #BART Fine-tuning

Downloads 25

Release Time : 3/2/2022

Model Overview

A fine-tuned BART-large-xsum model specifically designed for generating abstractive summaries from dialogue text.

Model Features

Dialogue Summarization

Summarization capability optimized specifically for dialogue text.

High-Quality Abstractive Summaries

Capable of generating fluent and coherent abstractive summaries, not just extracting key sentences.

SAMSum Dataset Fine-tuning

Specially fine-tuned on a high-quality, human-annotated dialogue summarization dataset.

Model Capabilities

Dialogue Understanding

Text Summarization

Natural Language Processing

Use Cases

Dialogue Analysis

Customer Support Dialogue Summarization

Automatically generate summaries of key content from customer support dialogues.

Helps quickly understand customer issues and solutions.

Meeting Minutes Summarization

Extract key decisions and action items from meeting dialogues.

Improves efficiency in meeting minutes organization.

🚀 bart-large-xsum-samsum

This model is designed for abstractive text summarization, fine - tuned on the Samsum dataset. It effectively summarizes dialogues, offering high - quality results.

🚀 Quick Start

This model bart-large-xsum-samsum is fine - tuned from facebook/bart-large-xsum on the Samsum dataset.

💻 Usage Examples

Basic Usage

from transformers import pipeline
summarizer = pipeline("summarization", model="knkarthick/bart-large-xsum-samsum")
conversation = '''Hannah: Hey, do you have Betty's number?
Amanda: Lemme check
Amanda: Sorry, can't find it.
Amanda: Ask Larry
Amanda: He called her last time we were at the park together
Hannah: I don't know him well
Amanda: Don't be shy, he's very nice
Hannah: If you say so..
Hannah: I'd rather you texted him
Amanda: Just text him 🙂
Hannah: Urgh.. Alright
Hannah: Bye
Amanda: Bye bye                                       
'''
summarizer(conversation)

📄 License

This model is licensed under the Apache - 2.0 license.

📚 Documentation

Model Information

Property	Details
Model Type	bart, seq2seq, summarization
Training Data	samsum

Model Performance

The bart-large-xsum-samsum model has been evaluated on the SAMSum Corpus for abstractive text summarization. The following table shows the ROUGE scores:

Task	Dataset	Metric	Value
Abstractive Text Summarization	SAMSum Corpus	Validation ROUGE - 1	54.3921
Abstractive Text Summarization	SAMSum Corpus	Validation ROUGE - 2	29.8078
Abstractive Text Summarization	SAMSum Corpus	Validation ROUGE - L	45.1543
Abstractive Text Summarization	SAMSum Corpus	Test ROUGE - 1	53.3059
Abstractive Text Summarization	SAMSum Corpus	Test ROUGE - 2	28.355
Abstractive Text Summarization	SAMSum Corpus	Test ROUGE - L	44.0953

Widget Example

You can test the model with the following dialogue:

Hannah: Hey, do you have Betty's number?
Amanda: Lemme check
Amanda: Sorry, can't find it.
Amanda: Ask Larry
Amanda: He called her last time we were at the park together
Hannah: I don't know him well
Amanda: Don't be shy, he's very nice
Hannah: If you say so..
Hannah: I'd rather you texted him
Amanda: Just text him 🙂
Hannah: Urgh.. Alright
Hannah: Bye
Amanda: Bye bye

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