ADD : Preprocessing

README.md

@@ -14,8 +14,10 @@ deplot_kr은 google의 pix2struct 구조를 기반으로 한 한국어 image-to-
 
 ## How to use
 
-You can run a prediction by input an image.
-Model predict the data table of text form in the image.
+You can run a prediction by input an image.    
+Model predict the data table of text form in the image.    
+    
+이미지를 모델에 입력하면 모델은 이미지로부터 표 형태의 데이터 테이블을 예측합니다.    
 
 ```python
 from transformers import Pix2StructForConditionalGeneration, Pix2StructImageProcessor, AutoTokenizer, Pix2StructProcessor
@@ -42,6 +44,14 @@ print(processor.batch_decode(deplot_generated_ids, skip_special_token=True)[0])
 
 ### Preprocessing
 
+[Liu et al.(2023)](https://arxiv.org/pdf/2212.10505.pdf) 에 따라,   
+According to [Liu et al.(2023)](https://arxiv.org/pdf/2212.10505.pdf)...     
+
+- markdown format
+- | : seperating cells (열 구분)
+- \n : seperating rows (행 구분)       
+
+
 ### Train
 
 The model was trained in a TPU environment.