Heuristic approach to curate disease taxonomy beyond nosology-based standards

Environment setting: python version : 3.7.0

1、Infodemiological study

Experimental corpus：GDELT Summary

• The textual and visual narratives of different queries
• 65 multilingual online news
• Machine translate capacity
• Network image recognition capacity

2、Historiographical study

Experimental corpus：Google Books Ngram Corpus

• n-grams from approximately 8 million books
• 6% of all books published in Eight languages
  • English
  • Hebrew
  • French
  • German
  • Spanish
  • Russian
  • Italian
  • Chinese
• Book data logs from 1500 to 2019

3、Semantic similarity experiments

Experimental corpus

• BERT [ the BookCorpus (800M words) and English Wikipedia (2,500M words) ]
• PubMedBERT [ PubMed abstracts (14M abstracts, 3.2B words, 21GB) ]

4、Semantic drift experiments

Experimental corpus：Google Books Ngram Corpus

Citing

Code for our paper "Heuristic approach to curate disease taxonomy beyond nosology-based standards". Please cite our paper if you find this repository helpful in your research.