code and data catalog for Disentangling the cultural evolution of ancient China: a digital humanities perspective
code
finetuning the model: python3 Main.py
detect similar texts: python3 unit_new.py
count sentence number: python3 stat.py
inference intertextuality: python3 indir.py
data catalog
The catalog of books in this corpus is given in 'data catalog.csv'.
Textual data is from two open websites, http://www.xueheng.net and http://www.daizhige.org/.
online platform
We show the corpus and results with data analysis functions on an online platform: http://evolution.pkudh.xyz/
It is now publicly accessible. Using Peking University VPN access can speed up the response.
*If the connection fails, it means we are maintaining the device or upgrading the system, please try again later.