Update README.md

README.md

@@ -37,9 +37,9 @@ Adopting a unified framework to handle multiple information extraction tasks, AI
 
 参考论文：[Unified BERT for Few-shot Natural Language Understanding](https://arxiv.org/abs/2206.12094)
 
-UBERT是[2022年AIWIN世界人工智能创新大赛：中文保险小样本多任务竞赛](http://ailab.aiwin.org.cn/competitions/68#results)的冠军解决方案。我们开发了一个基于类似BERT的骨干的多任务、多目标、统一的抽取任务框架。我们的UBERT在比赛A榜和B榜上均取得了第一名。因为比赛中的数据集在比赛结束后不再可用，我们开源的UBERT从多个任务中收集了70多个数据集（共1,065,069个样本）来进行预训练，并且我们选择了[MacBERT](https://huggingface.co/hfl/chinese-macbert-base)作为骨干网络。除了支持开箱即用之外，我们的UBERT还可以用于各种场景，如NLI、实体识别和阅读理解。示例代码可以在[Github](https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/dev/yangping/fengshen/examples/ubert)中找到。
+UBERT是[2022年AIWIN世界人工智能创新大赛：中文保险小样本多任务竞赛](http://ailab.aiwin.org.cn/competitions/68#results)的冠军解决方案。我们开发了一个基于类似BERT的骨干的多任务、多目标、统一的抽取任务框架。我们的UBERT在比赛A榜和B榜上均取得了第一名。因为比赛中的数据集在比赛结束后不再可用，我们开源的UBERT从多个任务中收集了70多个数据集（共1,065,069个样本）来进行预训练，并且我们选择了[MacBERT-Base](https://huggingface.co/hfl/chinese-macbert-base)作为骨干网络。除了支持开箱即用之外，我们的UBERT还可以用于各种场景，如NLI、实体识别和阅读理解。示例代码可以在[Github](https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/dev/yangping/fengshen/examples/ubert)中找到。
 
-UBERT was the winner solution in the [2022 AIWIN ARTIFICIAL INTELLIGENCE WORLD INNOVATIONS: Chinese Insurance Small Sample Multi-Task](http://ailab.aiwin.org.cn/competitions/68#results). We developed a unified framework based on BERT-like backbone for multiple tasks and objectives. Our UBERT owns first place, as described in leaderboards A and B. In addition to the unavailable datasets in the challenge, we carefully collect over 70 datasets (1,065,069 samples in total) from a variety of tasks for open-source UBERT. Moreover, we apply [MacBERT](https://huggingface.co/hfl/chinese-macbert-base) as the backbone. Besides out-of-the-box functionality, our UBERT can be employed in various scenarios such as NLI, entity recognition, and reading comprehension. The example codes can be found in [Github](https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/dev/yangping/fengshen/examples/ubert).
+UBERT was the winner solution in the [2022 AIWIN ARTIFICIAL INTELLIGENCE WORLD INNOVATIONS: Chinese Insurance Small Sample Multi-Task](http://ailab.aiwin.org.cn/competitions/68#results). We developed a unified framework based on BERT-like backbone for multiple tasks and objectives. Our UBERT owns first place, as described in leaderboards A and B. In addition to the unavailable datasets in the challenge, we carefully collect over 70 datasets (1,065,069 samples in total) from a variety of tasks for open-source UBERT. Moreover, we apply [MacBERT-Base](https://huggingface.co/hfl/chinese-macbert-base) as the backbone. Besides out-of-the-box functionality, our UBERT can be employed in various scenarios such as NLI, entity recognition, and reading comprehension. The example codes can be found in [Github](https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/dev/yangping/fengshen/examples/ubert).
 
 ## 使用 Usage