kira231/marie

Python implementation of MARIE (context-aware term mapping with string matching and embedding vectors)

MARIE (context-aware term mapping with string matching and embedding vectors)

• MARIE (context-aware term mapping with string matching and embedding vectors) is a tool to map a hospital’s unique terms to standardized clinical terminologies.
• By incorporating both string matching methods and term embedding vectors generated by BioBERT, it utilizes both structural and contextual information to calculate similarity measures between source and target terms.
• Compared to previous term mapping methods, our proposed method shows improved mapping accuracy.
• Furthermore, as a general mapping method, it can be easily expanded to incorporate any string matching or term embedding methods.

Warning

• This project does not provide BioBERT weights
• Please refer to https://github.com/dmis-lab/biobert and download BioBERT weights to save term embedding vectors as jsonl file

Funding

• This research was supported by a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, South Korea (grant number: HI19C0572)