Wikipedia-Wikidata Alignment

This repository is used to store wiki project code.

Data

data link : https://drive.google.com/drive/folders/1MKGlhBfFh1kzVCZj_nssp459zMFZ_lW4?usp=sharing

Medicine

wiki_data.pickle : store medicine wiki article and wiki data

Biology

raw : store compressed file for english and chinese wiki article and wiki data

preprocess:

  1. text_en.csv : english wiki article

  2. claim_en.csv : english wiki data

  3. text_zh.csv : chinese wiki article

  4. claim_zh.csv : chinese wiki data

Code

Medicine

Run model on medicine dataset

python run_wiki_medicine.py

Biology

Run model on biology dataset

python run_wiki_biology.py