Homonym Detection in Curated Bibliographies: Learning from dblp's Experience (full version)
This addresses the issue of author disambiguation for curators of bibliographic databases, but it is incremental as it applies an existing method to a new dataset.
The paper tackled the problem of identifying homonymous author profiles in bibliographic repositories like dblp, using a multilayer perceptron approach, and achieved evaluation results on a novel gold-standard dataset derived from manual curation.
Identifying (and fixing) homonymous and synonymous author profiles is one of the major tasks of curating personalized bibliographic metadata repositories like the dblp computer science bibliography. In this paper, we present and evaluate a machine learning approach to identify homonymous author bibliographies using a simple multilayer perceptron setup. We train our model on a novel gold-standard data set derived from the past years of active, manual curation at the dblp computer science bibliography.