Update README.md

README.md

@@ -33,7 +33,7 @@ The MacBERT with 325M parameters is pre-trained for Chinese text-matching tasks,
 
 为了提高模型在句子匹配上的效果，我们收集了大量句子匹配数据进行预训练，随后在FewCLUE的BUSTM任务进行微调，所有的训练均基于我们提出的UniMC框架。最终结果表明，3.25亿参数的模型通过我们的训练策略可以在句子匹配任务上超过1.3亿参数的大模型。
 
-To imporve the model performance on the text-matching task, we collected numerous text-matching datasets for pre-training. Then the model was finetuned on a specfic text-matching task, BUSTM from FewCLUE. All the training is based on the UniMC framework we proposed. The results show that our model with 325M parameters could surpass the model with 1.3B paramters on the text-matching task via our training strategies.
+To improve the model performance on the text-matching task, we collected numerous text-matching datasets for pre-training. Then the model was finetuned on a specific text-matching task, BUSTM from FewCLUE. All the training is based on the UniMC framework we proposed. The results show that our model with 325M parameters could surpass the model with 1.3B parameters on the text-matching task via our training strategies.
 
 ### 下游效果 Performance