🚀 bart-large-xsum-samsum

bart-large-xsum-samsum 模型基于序列到序列（seq2seq）架构，利用 BART 模型进行抽象文本摘要任务，可有效处理对话数据的摘要生成，在 SAMSum 数据集上表现出色。

🚀 快速开始

本模型是在 Samsum 数据集上对 facebook/bart-large-xsum 进行微调得到的。

💻 使用示例

基础用法

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)

📚 详细文档

模型信息

评估指标

该模型在 SAMSum 数据集上的评估指标如下：

示例对话

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

📄 许可证

本模型使用 Apache 2.0 许可证。