Randeng-Pegasus-523M-Summary-Chinese-V1
- Github: Fengshenbang-LM
- Docs: Fengshenbang-Docs
简介 Brief Introduction
善于处理摘要任务，在数个中文摘要数据集上微调后的，中文版的PAGASUS-large。
Good at solving text summarization tasks, after fine-tuning on multiple Chinese text summarization datasets, Chinese PAGASUS-large.
模型分类 Model Taxonomy
| 需求 Demand | 任务 Task | 系列 Series | 模型 Model | 参数 Parameter | 额外 Extra |
|---|---|---|---|---|---|
| 通用 General | 自然语言转换 NLT | 燃灯 Randeng | PEFASUS | 523M | 文本摘要任务-中文 Summary-Chinese |
模型信息 Model Information
参考论文：PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
基于Randeng-Pegasus-523M-Chinese，我们在收集的7个中文领域的文本摘要数据集（约4M个样本），使用实体过滤后数据集（约1.8M）重新微调，在不损伤下游指标的情况下提升了摘要对原文的忠实度，得到了summary-v1版本。这7个数据集为：education, new2016zh, nlpcc, shence, sohu, thucnews和weibo。
Based on Randeng-Pegasus-523M-Chinese, we fine-tuned a text summarization version (summary-v1) on a filted dataset(1.8M), which we use entitys to filter these 7 Chinese text summarization datasets, with totaling around 4M samples. We can improve the faithfulness of summaries without damage to the downstream task, eg. Rouge-L on lcsts. The datasets include: education, new2016zh, nlpcc, shence, sohu, thucnews and weibo.
下游效果 Performance
| datasets | rouge-1 | rouge-2 | rouge-L |
|---|---|---|---|
| LCSTS | 46.94 | 33.92 | 43.51 |
使用 Usage
from transformers import PegasusForConditionalGeneration
# Need to download tokenizers_pegasus.py and other Python script from Fengshenbang-LM github repo in advance,
# or you can download tokenizers_pegasus.py and data_utils.py in https://huggingface.co/IDEA-CCNL/Randeng_Pegasus_523M/tree/main
# Strongly recommend you git clone the Fengshenbang-LM repo:
# 1. git clone https://github.com/IDEA-CCNL/Fengshenbang-LM
# 2. cd Fengshenbang-LM/fengshen/examples/pegasus/
# and then you will see the tokenizers_pegasus.py and data_utils.py which are needed by pegasus model
from tokenizers_pegasus import PegasusTokenizer
model = PegasusForConditionalGeneration.from_pretrained("IDEA-CCNL/Randeng-Pegasus-523M-Summary-Chinese-V1")
tokenizer = PegasusTokenizer.from_pretrained("IDEA-CCNL/Randeng-Pegasus-523M-Summary-Chinese-V1")
text = "在北京冬奥会自由式滑雪女子坡面障碍技巧决赛中，中国选手谷爱凌夺得银牌。祝贺谷爱凌！今天上午，自由式滑雪女子坡面障碍技巧决赛举行。决赛分三轮进行，取选手最佳成绩排名决出奖牌。第一跳，中国选手谷爱凌获得69.90分。在12位选手中排名第三。完成动作后，谷爱凌又扮了个鬼脸，甚是可爱。第二轮中，谷爱凌在道具区第三个障碍处失误，落地时摔倒。获得16.98分。网友：摔倒了也没关系，继续加油！在第二跳失误摔倒的情况下，谷爱凌顶住压力，第三跳稳稳发挥，流畅落地！获得86.23分！此轮比赛，共12位选手参赛，谷爱凌第10位出场。网友：看比赛时我比谷爱凌紧张，加油！"
inputs = tokenizer(text, max_length=1024, return_tensors="pt")
# Generate Summary
summary_ids = model.generate(inputs["input_ids"])
tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
# model Output: 自由式滑雪女子坡面障碍技巧决赛谷爱凌摘银
引用 Citation
如果您在您的工作中使用了我们的模型，可以引用我们的论文：
If you are using the resource for your work, please cite the our paper:
@article{fengshenbang,
author = {Jiaxing Zhang and Ruyi Gan and Junjie Wang and Yuxiang Zhang and Lin Zhang and Ping Yang and Xinyu Gao and Ziwei Wu and Xiaoqun Dong and Junqing He and Jianheng Zhuo and Qi Yang and Yongfeng Huang and Xiayu Li and Yanghan Wu and Junyu Lu and Xinyu Zhu and Weifeng Chen and Ting Han and Kunhao Pan and Rui Wang and Hao Wang and Xiaojun Wu and Zhongshen Zeng and Chongpei Chen},
title = {Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence},
journal = {CoRR},
volume = {abs/2209.02970},
year = {2022}
}
也可以引用我们的网站:
You can also cite our website:
@misc{Fengshenbang-LM,
title={Fengshenbang-LM},
author={IDEA-CCNL},
year={2021},
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
}