{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ethnicity-sensitive-author-disambiguation","title":"Ethnicity sensitive author disambiguation using semi-supervised learning","arxiv_id":"1508.07744","date":"2015-08-31","proceeding":null,"authors":["Gilles Louppe","Hussein Al-Natsheh","Mateusz Susik","Eamonn Maguire"],"abstract":"Author name disambiguation in bibliographic databases is the problem of\ngrouping together scientific publications written by the same person,\naccounting for potential homonyms and/or synonyms. Among solutions to this\nproblem, digital libraries are increasingly offering tools for authors to\nmanually curate their publications and claim those that are theirs. Indirectly,\nthese tools allow for the inexpensive collection of large annotated training\ndata, which can be further leveraged to build a complementary automated\ndisambiguation system capable of inferring patterns for identifying\npublications written by the same person. Building on more than 1 million\npublicly released crowdsourced annotations, we propose an automated author\ndisambiguation solution exploiting this data (i) to learn an accurate\nclassifier for identifying coreferring authors and (ii) to guide the clustering\nof scientific publications by distinct authors in a semi-supervised way. To the\nbest of our knowledge, our analysis is the first to be carried out on data of\nthis size and coverage. With respect to the state of the art, we validate the\ngeneral pipeline used in most existing solutions, and improve by: (i) proposing\nphonetic-based blocking strategies, thereby increasing recall; and (ii) adding\nstrong ethnicity-sensitive features for learning a linkage function, thereby\ntailoring disambiguation to non-Western author names whenever necessary.","url_abs":"http://arxiv.org/abs/1508.07744v2","url_pdf":"http://arxiv.org/pdf/1508.07744v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ethnicity-sensitive-author-disambiguation","repo_url":"https://github.com/glouppe/paper-author-disambiguation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"blocking","task_name":"Blocking"},{"task_slug":"clustering","task_name":"Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1508.07744","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}