Comparative study of name disambiguation problem using a scalable blocking-based framework. On, B., Lee, D., Kang, J., & Mitra, P. In Proc. of the 5th ACM/IEEE-CS Joint Conf. on Digital libraries, pages 344--353, 2005.
doi  abstract   bibtex   
In this paper, we consider the problem of ambiguous author names in bibliographic citations, and comparatively study alternative approaches to identify and correct such name variants (e.g., "Vannevar Bush" and "V. Vush"). Our study is based on a scalable two-step framework, where step 1 is to substantially reduce the number of candidates via blocking, and step 2 is to measure the distance of two names via coauthor information. Combining four blocking methods and seven distance measures on four data sets, we present extensive experimental results, and identify combinations that are scalable and effective to disambiguate author names in citations.
@inproceedings{on_comparative_2005,
	title = {Comparative study of name disambiguation problem using a scalable blocking-based framework},
	isbn = {1-58113-876-8},
	doi = {10.1145/1065385.1065463},
	abstract = {In this paper, we consider the problem of ambiguous author names in bibliographic citations, and comparatively study alternative approaches to identify and correct such name variants (e.g., "Vannevar Bush" and "V. Vush"). Our study is based on a scalable two-step framework, where step 1 is to substantially reduce the number of candidates via blocking, and step 2 is to measure the distance of two names via coauthor information. Combining four blocking methods and seven distance measures on four data sets, we present extensive experimental results, and identify combinations that are scalable and effective to disambiguate author names in citations.},
	urldate = {2009-04-08TZ},
	booktitle = {Proc. of the 5th {ACM}/{IEEE}-{CS} {Joint} {Conf}. on {Digital} libraries},
	author = {On, Byung-Won and Lee, Dongwon and Kang, Jaewoo and Mitra, Prasenjit},
	year = {2005},
	keywords = {blocking, measuring distances, name disambiguation},
	pages = {344--353}
}

Downloads: 0