`bart-large-xsum-samsum`

This model was obtained by fine-tuning facebook/bart-large-xsum on Samsum dataset.

Usage

from transformers import pipeline

summarizer = pipeline("summarization", model="lidiya/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)

Training procedure

Colab notebook: https://colab.research.google.com/drive/1dul0Sg-TTMy9xZCJzmDRajXbyzDwtYx6?usp=sharing

Results

key	value
eval_rouge1	54.3921
eval_rouge2	29.8078
eval_rougeL	45.1543
eval_rougeLsum	49.942
test_rouge1	53.3059
test_rouge2	28.355
test_rougeL	44.0953
test_rougeLsum	48.9246

Downloads last month: 14,717

Safetensors

Model size

406M params

Tensor type

F32

Inference Examples

Summarization

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for lidiya/bart-large-xsum-samsum

Finetunes

2 models

Dataset used to train lidiya/bart-large-xsum-samsum

Spaces using lidiya/bart-large-xsum-samsum 5

Evaluation results

Validation ROUGE-1 on SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization
self-reported

54.392
Validation ROUGE-2 on SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization
self-reported

29.808
Validation ROUGE-L on SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization
self-reported

45.154
Test ROUGE-1 on SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization
self-reported

53.306
Test ROUGE-2 on SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization
self-reported

28.355
Test ROUGE-L on SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization
self-reported

44.095

View on Papers With Code