This paper reports an investigation of machine learning methods for the semi-automated creation of a BIBFRAME Work entity description within the RDF linked data editor Sinopia (https://sinopia.io). The automated subject indexing software Annif was configured with the Library of Congress Subject Headings (LCSH) vocabulary from the Linked Data Service at https://id.loc.gov/. The training corpus was comprised of 9.3 million titles and LCSH linked data references from the IvyPlus POD project (https://pod.stanford.edu/) and from Share-VDE (https://wiki.share-vde.org). Semi-automated processes were explored to support and extend, not replace, professional expertise.
%0 Journal Article
%1 hahn_semi-automated_2021
%A Hahn, Jim
%D 2021
%J Cataloging & Classification Quarterly
%K formalerschliessung maschinelles_lernen
%N 8
%P 853--867
%R 10.1080/01639374.2021.2014011
%T Semi-automated methods for BIBFRAME work entity description
%U https://doi.org/10.1080/01639374.2021.2014011
%V 59
%X This paper reports an investigation of machine learning methods for the semi-automated creation of a BIBFRAME Work entity description within the RDF linked data editor Sinopia (https://sinopia.io). The automated subject indexing software Annif was configured with the Library of Congress Subject Headings (LCSH) vocabulary from the Linked Data Service at https://id.loc.gov/. The training corpus was comprised of 9.3 million titles and LCSH linked data references from the IvyPlus POD project (https://pod.stanford.edu/) and from Share-VDE (https://wiki.share-vde.org). Semi-automated processes were explored to support and extend, not replace, professional expertise.
@article{hahn_semi-automated_2021,
abstract = {This paper reports an investigation of machine learning methods for the semi-automated creation of a BIBFRAME Work entity description within the RDF linked data editor Sinopia (https://sinopia.io). The automated subject indexing software Annif was configured with the Library of Congress Subject Headings (LCSH) vocabulary from the Linked Data Service at https://id.loc.gov/. The training corpus was comprised of 9.3 million titles and LCSH linked data references from the IvyPlus POD project (https://pod.stanford.edu/) and from Share-VDE (https://wiki.share-vde.org). Semi-automated processes were explored to support and extend, not replace, professional expertise.},
added-at = {2022-02-18T16:38:17.000+0100},
author = {Hahn, Jim},
biburl = {https://www.bibsonomy.org/bibtex/23deca8e0a86754f38ecbd6ae330c029f/lepsky},
doi = {10.1080/01639374.2021.2014011},
interhash = {d821cb1562f92f07991571c4740b765f},
intrahash = {3deca8e0a86754f38ecbd6ae330c029f},
issn = {0163-9374},
journal = {Cataloging \& Classification Quarterly},
keywords = {formalerschliessung maschinelles_lernen},
month = nov,
note = {Publisher: Routledge\_eprint: https://doi.org/10.1080/01639374.2021.2014011},
number = 8,
pages = {853--867},
timestamp = {2022-02-18T16:41:52.000+0100},
title = {Semi-automated methods for {BIBFRAME} work entity description},
url = {https://doi.org/10.1080/01639374.2021.2014011},
urldate = {2022-02-15},
volume = 59,
year = 2021
}