Update README.md

README.md

@@ -22,7 +22,7 @@ from transformers import AutoTokenizer, AutoModelForMaskedLM
 tokenizer = AutoTokenizer.from_pretrained("conan1024hao/cjkbert-small")
 model = AutoModelForMaskedLM.from_pretrained("conan1024hao/cjkbert-small")
 ```
-You don't need any text segmentation when you fine-tune downstream tasks. (For Korean, you may obtain better results if you apply KoNLPy morphological analysis to the data before fine-tuning.)
+You don't need any text segmentation when you fine-tune downstream tasks. (Though you may obtain better results if you apply morphological analysis to the data before fine-tuning.)
 
 ### Tokenization
 We use character-based tokenization with whole-word-masking strategy.