Vapur is an online entity-oriented search engine for the COVID-19 anthology. Vapur is empowered with a semantic inverted index that is created through named entity recognition and relation extraction on CORD-19 abstracts.
In order to run scripts from scratch, please follow these:
- Download CORD-19 Dataset
- Install Genia Sentence Splitter
- Run BERN on 127.0.0.1:8888
- Download our pretrained binary relation extraction model from Google Drive and run the relevant script to find related protein - compound pairs in COVID-19 literature.
Check out our search engine at https://tabilab.cmpe.boun.edu.tr/vapur and related Flask code in Demo folder.