MEETING SUMMARY BART LARGE XSUM SAMSUM DIALOGSUM
M
MEETING SUMMARY BART LARGE XSUM SAMSUM DIALOGSUM
由 knkarthick 开发
基于BART-large架构的序列到序列模型,专门针对会议摘要任务进行微调,支持多数据集训练
下载量 123
发布时间 : 3/2/2022
模型简介
该模型通过微调facebook/bart-large-xsum获得,专门用于生成抽象文本摘要,特别擅长处理对话和会议场景的摘要任务
模型特点
多数据集训练
在cnndaily/newyorkdaily/xsum/samsum/dialogsum等多个摘要数据集上进行微调
对话场景优化
特别针对会议记录和对话摘要场景进行优化
抽象摘要能力
能够生成非简单抽取式的、语义连贯的摘要
模型能力
文本摘要生成
对话内容压缩
会议记录精简
使用案例
会议记录处理
自动会议纪要生成
将冗长的会议对话自动生成简洁的要点摘要
生成符合人类写作习惯的会议纪要
新闻摘要
新闻内容精简
从长篇新闻报道中提取核心内容
生成保留关键信息的简短新闻摘要
🚀 会议摘要BART大模型
本项目基于BART架构,通过微调facebook/bart-large-xsum
模型得到,用于文本摘要任务。它可以处理多种类型的文本,如会议记录、新闻文章等,为用户提供高效准确的摘要生成服务。
🚀 快速开始
本模型是通过微调facebook/bart-large-xsum
得到的。以下是使用本模型进行文本摘要的示例代码:
💻 使用示例
基础用法
from transformers import pipeline
summarizer = pipeline("summarization", model="knkarthick/MEETING-SUMMARY-BART-LARGE-XSUM-SAMSUM-DIALOGSUM")
text = '''The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.
'''
summarizer(text)
高级用法
from transformers import pipeline
summarizer = pipeline("summarization", model="knkarthick/MEETING-SUMMARY-BART-LARGE-XSUM-SAMSUM-DIALOGSUM")
text = '''Bangalore is the capital and the largest city of the Indian state of Karnataka. It has a population of more than 8 million and a metropolitan population of around 11 million, making it the third most populous city and fifth most populous urban agglomeration in India. Located in southern India on the Deccan Plateau, at a height of over 900 m (3,000 ft) above sea level, Bangalore is known for its pleasant climate throughout the year. Its elevation is the highest among the major cities of India.The city's history dates back to around 890 CE, in a stone inscription found at the Nageshwara Temple in Begur, Bangalore. The Begur inscription is written in Halegannada (ancient Kannada), mentions 'Bengaluru Kalaga' (battle of Bengaluru). It was a significant turning point in the history of Bangalore as it bears the earliest reference to the name 'Bengaluru'. In 1537 CE, Kempé Gowdā – a feudal ruler under the Vijayanagara Empire – established a mud fort considered to be the foundation of modern Bangalore and its oldest areas, or petes, which exist to the present day.
After the fall of Vijayanagar empire in 16th century, the Mughals sold Bangalore to Chikkadevaraja Wodeyar (1673–1704), the then ruler of the Kingdom of Mysore for three lakh rupees. When Haider Ali seized control of the Kingdom of Mysore, the administration of Bangalore passed into his hands.
The city was captured by the British East India Company after victory in the Fourth Anglo-Mysore War (1799), who returned administrative control of the city to the Maharaja of Mysore. The old city developed in the dominions of the Maharaja of Mysore and was made capital of the Princely State of Mysore, which existed as a nominally sovereign entity of the British Raj. In 1809, the British shifted their cantonment to Bangalore, outside the old city, and a town grew up around it, which was governed as part of British India. Following India's independence in 1947, Bangalore became the capital of Mysore State, and remained capital when the new Indian state of Karnataka was formed in 1956. The two urban settlements of Bangalore – city and cantonment – which had developed as independent entities merged into a single urban centre in 1949. The existing Kannada name, Bengalūru, was declared the official name of the city in 2006.
Bangalore is widely regarded as the "Silicon Valley of India" (or "IT capital of India") because of its role as the nation's leading information technology (IT) exporter. Indian technological organisations are headquartered in the city. A demographically diverse city, Bangalore is the second fastest-growing major metropolis in India. Recent estimates of the metro economy of its urban area have ranked Bangalore either the fourth- or fifth-most productive metro area of India. As of 2017, Bangalore was home to 7,700 millionaires and 8 billionaires with a total wealth of $320 billion. It is home to many educational and research institutions. Numerous state-owned aerospace and defence organisations are located in the city. The city also houses the Kannada film industry. It was ranked the most liveable Indian city with a population of over a million under the Ease of Living Index 2020.
'''
summarizer(text)
📚 详细文档
模型信息
属性 | 详情 |
---|---|
模型类型 | BART大模型用于会议摘要 |
训练数据 | cnndaily/newyorkdaily/xsum/samsum/dialogsum |
评估指标 | rouge |
模型结果
任务 | 数据集 | 评估指标 | 值 |
---|---|---|---|
抽象文本摘要 | cnndaily/newyorkdaily/xsum/samsum/dialogsum | Validation ROGUE - 1 | NA |
抽象文本摘要 | cnndaily/newyorkdaily/xsum/samsum/dialogsum | Validation ROGUE - 2 | NA |
抽象文本摘要 | cnndaily/newyorkdaily/xsum/samsum/dialogsum | Validation ROGUE - L | NA |
抽象文本摘要 | cnndaily/newyorkdaily/xsum/samsum/dialogsum | Validation ROGUE - Lsum | NA |
抽象文本摘要 | cnndaily/newyorkdaily/xsum/samsum/dialogsum | Test ROGUE - 1 | NA |
抽象文本摘要 | cnndaily/newyorkdaily/xsum/samsum/dialogsum | Test ROGUE - 2 | NA |
抽象文本摘要 | cnndaily/newyorkdaily/xsum/samsum/dialogsum | Test ROGUE - L | NA |
抽象文本摘要 | cnndaily/newyorkdaily/xsum/samsum/dialogsum | Test ROGUE - Lsum | NA |
📄 许可证
本项目采用Apache 2.0许可证。
Bart Large Cnn
MIT
基于英语语料预训练的BART模型,专门针对CNN每日邮报数据集进行微调,适用于文本摘要任务
文本生成 英语
B
facebook
3.8M
1,364
Parrot Paraphraser On T5
Parrot是一个基于T5的释义框架,专为加速训练自然语言理解(NLU)模型而设计,通过生成高质量释义实现数据增强。
文本生成
Transformers

P
prithivida
910.07k
152
Distilbart Cnn 12 6
Apache-2.0
DistilBART是BART模型的蒸馏版本,专门针对文本摘要任务进行了优化,在保持较高性能的同时显著提升了推理速度。
文本生成 英语
D
sshleifer
783.96k
278
T5 Base Summarization Claim Extractor
基于T5架构的模型,专门用于从摘要文本中提取原子声明,是摘要事实性评估流程的关键组件。
文本生成
Transformers 英语

T
Babelscape
666.36k
9
Unieval Sum
UniEval是一个统一的多维评估器,用于自然语言生成任务的自动评估,支持多个可解释维度的评估。
文本生成
Transformers

U
MingZhong
318.08k
3
Pegasus Paraphrase
Apache-2.0
基于PEGASUS架构微调的文本复述模型,能够生成语义相同但表达不同的句子。
文本生成
Transformers 英语

P
tuner007
209.03k
185
T5 Base Korean Summarization
这是一个基于T5架构的韩语文本摘要模型,专为韩语文本摘要任务设计,通过微调paust/pko-t5-base模型在多个韩语数据集上训练而成。
文本生成
Transformers 韩语

T
eenzeenee
148.32k
25
Pegasus Xsum
PEGASUS是一种基于Transformer的预训练模型,专门用于抽象文本摘要任务。
文本生成 英语
P
google
144.72k
198
Bart Large Cnn Samsum
MIT
基于BART-large架构的对话摘要模型,专为SAMSum语料库微调,适用于生成对话摘要。
文本生成
Transformers 英语

B
philschmid
141.28k
258
Kobart Summarization
MIT
基于KoBART架构的韩语文本摘要模型,能够生成韩语新闻文章的简洁摘要。
文本生成
Transformers 韩语

K
gogamza
119.18k
12
精选推荐AI模型
Llama 3 Typhoon V1.5x 8b Instruct
专为泰语设计的80亿参数指令模型,性能媲美GPT-3.5-turbo,优化了应用场景、检索增强生成、受限生成和推理任务
大型语言模型
Transformers 支持多种语言

L
scb10x
3,269
16
Cadet Tiny
Openrail
Cadet-Tiny是一个基于SODA数据集训练的超小型对话模型,专为边缘设备推理设计,体积仅为Cosmo-3B模型的2%左右。
对话系统
Transformers 英语

C
ToddGoldfarb
2,691
6
Roberta Base Chinese Extractive Qa
基于RoBERTa架构的中文抽取式问答模型,适用于从给定文本中提取答案的任务。
问答系统 中文
R
uer
2,694
98
智启未来,您的人工智能解决方案智库
简体中文