Computational Curation and the Application of Large-Scale Vocabularies

Paper presents an exploratory case study comparing stemming and lemmatization results for the automatic application of large-scale controlled vocabularies processed against archival encyclopedia entries. The results report relative recall and precision evaluations across both results. Research shows that while stemming has a higher relative recall, lemmatization results in a higher relevance score and eliminates the over-stemming challenges. Results provide insight into improving automatic curation workflows for archival resources.