Author disambiguation and publication assignment

Abstract

Described herein are computer-implemented systems and methods for automatically disambiguating author names for a plurality of publications so as to create clusters of author name mentions that are with high probability associated with a single author identity for each cluster. Also described are systems and methods for assigning the clusters to respective unique author identities, automatically and/or based on human input (e.g., as received from authors, co-authors, or administrative curators).

What is claimed is: 
     
         1 . A method, executed by a computing system, for assigning publications to authors, the method comprising:
 for each of a plurality of publications, generating an author-name-mention data structure for each author name listed on the publication, the author-name-mention data structure comprising at least an identifier of the publication and the listed author name;   automatically clustering the author-name-mention data structures to form clusters each representing a disambiguated cluster author and containing one or more publications within the cluster;   automatically identifying, among a plurality of individuals uniquely represented within the computing system, candidate authors for at least some of the clusters;   for at least one of the clusters and the candidate author identified for the cluster,
 presenting a user of the computing system with at least a subset of the one or more publications within the cluster, 
 soliciting confirmation from the user that the candidate author authored the publications within the subset, and 
 in response to, and at least in part based on, receipt of the confirmation, assigning all publications within the cluster to the candidate author.