CiteSeer and Google-Scholar are huge digital libraries which provide
access to (computer-)science publications. Both collections are operated like
specialized search engines, they crawl the web with little human intervention
and analyse the documents to classifiy them and to extract some metadata from
the full texts. On the other hand there are traditional bibliographic data bases
like INSPEC for engineering and PubMed for medicine. For the field of computer science the DBLP service evolved from a small specialized bibliography
to a digital library covering most subfields of computer science. The collections
of the second group are maintained with massive human effort. On the long
term this investment is only justified if data quality of the manually maintained
collections remains much higher than that of the search engine style collections.
In this paper we discuss management and algorithmic issues of data quality. We
focus on the special problem of person names.
%0 Conference Paper
%1 ley2006maintaining
%A Ley, Michael
%A Reuther, Patrick
%D 2006
%K dblp nameDisambiguation scienceontwitter twitterScholar
%T Maintaining an Online Bibliographical Database: The Problem of Data Quality.
%U http://pdf.aminer.org/000/300/568/data_cleaning_and_xml_the_dblp_experience.pdf
%X CiteSeer and Google-Scholar are huge digital libraries which provide
access to (computer-)science publications. Both collections are operated like
specialized search engines, they crawl the web with little human intervention
and analyse the documents to classifiy them and to extract some metadata from
the full texts. On the other hand there are traditional bibliographic data bases
like INSPEC for engineering and PubMed for medicine. For the field of computer science the DBLP service evolved from a small specialized bibliography
to a digital library covering most subfields of computer science. The collections
of the second group are maintained with massive human effort. On the long
term this investment is only justified if data quality of the manually maintained
collections remains much higher than that of the search engine style collections.
In this paper we discuss management and algorithmic issues of data quality. We
focus on the special problem of person names.
@inproceedings{ley2006maintaining,
abstract = {CiteSeer and Google-Scholar are huge digital libraries which provide
access to (computer-)science publications. Both collections are operated like
specialized search engines, they crawl the web with little human intervention
and analyse the documents to classifiy them and to extract some metadata from
the full texts. On the other hand there are traditional bibliographic data bases
like INSPEC for engineering and PubMed for medicine. For the field of computer science the DBLP service evolved from a small specialized bibliography
to a digital library covering most subfields of computer science. The collections
of the second group are maintained with massive human effort. On the long
term this investment is only justified if data quality of the manually maintained
collections remains much higher than that of the search engine style collections.
In this paper we discuss management and algorithmic issues of data quality. We
focus on the special problem of person names.},
added-at = {2013-08-12T12:09:13.000+0200},
author = {Ley, Michael and Reuther, Patrick},
biburl = {https://www.bibsonomy.org/bibtex/23c18aa355eac6d46a7c5c5b5cc3bb737/asmelash},
interhash = {8300ca4f078e5d8f5af2ad4ae08b8f58},
intrahash = {3c18aa355eac6d46a7c5c5b5cc3bb737},
keywords = {dblp nameDisambiguation scienceontwitter twitterScholar},
month = {January},
timestamp = {2013-08-12T12:09:14.000+0200},
title = {Maintaining an Online Bibliographical Database: The Problem of Data Quality.},
url = {http://pdf.aminer.org/000/300/568/data_cleaning_and_xml_the_dblp_experience.pdf},
year = 2006
}