Update README.md

README.md

@@ -28,11 +28,12 @@ You can use the model directly with a pipeline for text generation:
 
 ## Training data
 
-Training data contains 3,000,000 ancient Chinese which are collected by [daizhigev20](https://github.com/garychowcmu/daizhigev20).
+Training data contains 3,000,000 ancient Chinese which are collected by [daizhigev20](https://github.com/garychowcmu/daizhigev20). Since part of ancient corpus has no punctuation, we used the [ancient Chinese punctuation system](https://seg.shenshen.wiki) developed by [BNU ICIP lab](http://icip.bnu.edu.cn/).　
+
 
 ## Training procedure
 
-The model is pre-trained by [UER-py](https://github.com/dbiir/UER-py/) on [Tencent Cloud TI-ONE](https://cloud.tencent.com/product/tione/). We pre-train 500,000 steps with a sequence length of 320. We use extended vocabulary to handle out-of-vocabulary words. The Chinese character that occurs greater than or equal to 100 in ancient chinese corpus is added to the vocabulary.
+The model is pre-trained by [UER-py](https://github.com/dbiir/UER-py/) on [Tencent Cloud TI-ONE](https://cloud.tencent.com/product/tione/). We pre-train 500,000 steps with a sequence length of 320. We use extended vocabulary to handle out-of-vocabulary words. The Chinese character that occurs greater than or equal to 100 in ancient Chinese corpus is added to the vocabulary.
 
 ```
 python3 preprocess.py --corpus_path corpora/ancient_chinese.txt \
@@ -72,4 +73,6 @@ python3 scripts/convert_gpt2_from_uer_to_huggingface.py --input_model_path ancie
   pages={241},
   year={2019}
 }
+
+胡韧奋,李绅,诸雨辰.基于深层语言模型的古汉语知识表示及自动断句研究[C].第十八届中国计算语言学大会（CCL 2019）.
 ```