dspinellis / alexandria3k

Local relational access to openly-available publication data sets
GNU General Public License v3.0
79 stars 14 forks source link

Process to disambiguate author affiliations using gpt-4 #40

Open dtgupta opened 6 months ago

dtgupta commented 6 months ago

This process adds a different dimension to author affiliation disambiguation. It uses NLP to extract affiliations from text. This process produces better results than the currently implemented matching strategy. It has a matching rate of 81.24% as compared to 36.73% of the currently implemented algorithm. It also performs much better to match authors to multiple affiliations. This process adds value to the project as it helps researchers with more accurate affiliation results.