Supplementary Material Accompanying the Study "First Steps Towards the Integration of Resources on Historical Glossing Traditions in the History of Chinese: A Collection of Standardized Fǎnqiè Spellings from the Guǎngyùn"

Cite the original paper as:

Pulini, Michele and List, Johann-Mattis (2024): First Steps Towards the Integration of Resources on Historical Glossing Traditions in the History of Chinese: A Collection of Standardized Fǎnqiè Spellings from the Guǎngyùn. In: LREC-COLING.

Installation

To install the code that we used to analyze the data, make sure to have Python installed, and then just type:

$ pip install -r requirements.txt

Analyses

There are two major steps. First, we download the data from the EDICTOR tool, second, we run the script to check for inconsistencies and compare with other sources.

The first script can be called as follows:

$ python download.py

The second script can be run as follows:

$ python predict-all.py