From raw affiliations to organization identifiers. Kallipoliti, M., Chatzopoulos, S., Baglioni, M., Adamidi, E., Koloveas, P., & Vergoulis, T. May, 2025. arXiv:2505.07577 [cs]
Paper doi abstract bibtex Accurate affiliation matching, which links affiliation strings to standardized organization identifiers, is critical for improving research metadata quality, facilitating comprehensive bibliometric analyses, and supporting data interoperability across scholarly knowledge bases. Existing approaches fail to handle the complexity of affiliation strings that often include mentions of multiple organizations or extraneous information. In this paper, we present AffRo, a novel approach designed to address these challenges, leveraging advanced parsing and disambiguation techniques. We also introduce AffRoDB, an expert-curated dataset to systematically evaluate affiliation matching algorithms, ensuring robust benchmarking. Results demonstrate the effectiveness of AffRp in accurately identifying organizations from complex affiliation strings.
@misc{kallipoliti_raw_2025,
title = {From raw affiliations to organization identifiers},
url = {http://arxiv.org/abs/2505.07577},
doi = {10.48550/arXiv.2505.07577},
abstract = {Accurate affiliation matching, which links affiliation strings to standardized organization identifiers, is critical for improving research metadata quality, facilitating comprehensive bibliometric analyses, and supporting data interoperability across scholarly knowledge bases. Existing approaches fail to handle the complexity of affiliation strings that often include mentions of multiple organizations or extraneous information. In this paper, we present AffRo, a novel approach designed to address these challenges, leveraging advanced parsing and disambiguation techniques. We also introduce AffRoDB, an expert-curated dataset to systematically evaluate affiliation matching algorithms, ensuring robust benchmarking. Results demonstrate the effectiveness of AffRp in accurately identifying organizations from complex affiliation strings.},
urldate = {2025-05-16},
publisher = {arXiv},
author = {Kallipoliti, Myrto and Chatzopoulos, Serafeim and Baglioni, Miriam and Adamidi, Eleni and Koloveas, Paris and Vergoulis, Thanasis},
month = may,
year = {2025},
note = {arXiv:2505.07577 [cs]},
keywords = {Computer Science - Digital Libraries, Computer Science - Information Retrieval},
}
Downloads: 0
{"_id":"QeownYqt5LAdxj3cX","bibbaseid":"kallipoliti-chatzopoulos-baglioni-adamidi-koloveas-vergoulis-fromrawaffiliationstoorganizationidentifiers-2025","author_short":["Kallipoliti, M.","Chatzopoulos, S.","Baglioni, M.","Adamidi, E.","Koloveas, P.","Vergoulis, T."],"bibdata":{"bibtype":"misc","type":"misc","title":"From raw affiliations to organization identifiers","url":"http://arxiv.org/abs/2505.07577","doi":"10.48550/arXiv.2505.07577","abstract":"Accurate affiliation matching, which links affiliation strings to standardized organization identifiers, is critical for improving research metadata quality, facilitating comprehensive bibliometric analyses, and supporting data interoperability across scholarly knowledge bases. Existing approaches fail to handle the complexity of affiliation strings that often include mentions of multiple organizations or extraneous information. In this paper, we present AffRo, a novel approach designed to address these challenges, leveraging advanced parsing and disambiguation techniques. We also introduce AffRoDB, an expert-curated dataset to systematically evaluate affiliation matching algorithms, ensuring robust benchmarking. Results demonstrate the effectiveness of AffRp in accurately identifying organizations from complex affiliation strings.","urldate":"2025-05-16","publisher":"arXiv","author":[{"propositions":[],"lastnames":["Kallipoliti"],"firstnames":["Myrto"],"suffixes":[]},{"propositions":[],"lastnames":["Chatzopoulos"],"firstnames":["Serafeim"],"suffixes":[]},{"propositions":[],"lastnames":["Baglioni"],"firstnames":["Miriam"],"suffixes":[]},{"propositions":[],"lastnames":["Adamidi"],"firstnames":["Eleni"],"suffixes":[]},{"propositions":[],"lastnames":["Koloveas"],"firstnames":["Paris"],"suffixes":[]},{"propositions":[],"lastnames":["Vergoulis"],"firstnames":["Thanasis"],"suffixes":[]}],"month":"May","year":"2025","note":"arXiv:2505.07577 [cs]","keywords":"Computer Science - Digital Libraries, Computer Science - Information Retrieval","bibtex":"@misc{kallipoliti_raw_2025,\n\ttitle = {From raw affiliations to organization identifiers},\n\turl = {http://arxiv.org/abs/2505.07577},\n\tdoi = {10.48550/arXiv.2505.07577},\n\tabstract = {Accurate affiliation matching, which links affiliation strings to standardized organization identifiers, is critical for improving research metadata quality, facilitating comprehensive bibliometric analyses, and supporting data interoperability across scholarly knowledge bases. Existing approaches fail to handle the complexity of affiliation strings that often include mentions of multiple organizations or extraneous information. In this paper, we present AffRo, a novel approach designed to address these challenges, leveraging advanced parsing and disambiguation techniques. We also introduce AffRoDB, an expert-curated dataset to systematically evaluate affiliation matching algorithms, ensuring robust benchmarking. Results demonstrate the effectiveness of AffRp in accurately identifying organizations from complex affiliation strings.},\n\turldate = {2025-05-16},\n\tpublisher = {arXiv},\n\tauthor = {Kallipoliti, Myrto and Chatzopoulos, Serafeim and Baglioni, Miriam and Adamidi, Eleni and Koloveas, Paris and Vergoulis, Thanasis},\n\tmonth = may,\n\tyear = {2025},\n\tnote = {arXiv:2505.07577 [cs]},\n\tkeywords = {Computer Science - Digital Libraries, Computer Science - Information Retrieval},\n}\n\n","author_short":["Kallipoliti, M.","Chatzopoulos, S.","Baglioni, M.","Adamidi, E.","Koloveas, P.","Vergoulis, T."],"key":"kallipoliti_raw_2025","id":"kallipoliti_raw_2025","bibbaseid":"kallipoliti-chatzopoulos-baglioni-adamidi-koloveas-vergoulis-fromrawaffiliationstoorganizationidentifiers-2025","role":"author","urls":{"Paper":"http://arxiv.org/abs/2505.07577"},"keyword":["Computer Science - Digital Libraries","Computer Science - Information Retrieval"],"metadata":{"authorlinks":{}}},"bibtype":"misc","biburl":"https://api.zotero.org/groups/4790165/items?key=gGXRwyXLTBDTPjwmoAXo5O9G&format=bibtex&limit=100","dataSources":["wkZmECJAmJTTcjXCL","txmtuJDjhqHfaZE3C","ttiB3rxTuWH3fiHv3","XooGe8m5uEyMY8yz7","ez36gbfWfBmHWbPMB"],"keywords":["computer science - digital libraries","computer science - information retrieval"],"search_terms":["raw","affiliations","organization","identifiers","kallipoliti","chatzopoulos","baglioni","adamidi","koloveas","vergoulis"],"title":"From raw affiliations to organization identifiers","year":2025}