In this pilot study we examine the performance of text-based profiling in recovering a set of validated inventor-author links.
In a first step we match patents and publications solely based on their similarity in content. Next, we compare inventor and
author names on the highest ranked matches for the occurrence of name matches. Finally, we compare these candidate matches
with the names listed in a validated set of inventor-author names. Our text-based profile methodology performs significantly
better than a random matching of patents and publications, suggesting that text-based profiling is a valuable complementary
tool to the name searches used in previous studies.