DCC Research Fellow

HATII
Office: Attic
George Service House
11 University Gardens
Glasgow
G12 8QH

Tel: +44 (0)141 330 8594
Fax: +44 (0)141 330 3788
Email: y.kim@hatii.arts.gla.ac.uk

Yunhyong Kim has been on the academic research staff of HATII since May 2005. She has a Ph.D in Mathematics from the University of Cambridge and an MSc. in Speech and Language Processing from Linguistics and English at the University of Edinburgh.

Yunhyong collaborates with Professor Seamus Ross on a Digital Curation Centre (DCC) project to scope methods of Automated Semantic Metadata Extraction for the automated ingest of digital material into digital repositories. She is also a member of the Association for Computing Machinery and the Association for Computational Linguistics.

Teaching

• Co-convenor of the course Management, Curation and Preservation of Digital Material in the MSc. in Inormation Management and Preservation

Research

Yunhyong's research focus is in machine learning methods that are applied to information management, use, and preservation as well as knowledge discovery. In particular, her research has addressed the detection of implicit citations in the form of pronouns found in scientific papers, and currently she has been studying automated genre classification of documents as a first step towards identifying the structural representation of text.

Publications

Y.Kim (2004) The Lie Algebra Cohomology of Jets. Journal of Lie Theory, 14(1): 271--286.
http://www.emis.de/journals/JLT/vol.14_no.1/11.html

Y. Kim and S. Ross (2006) Genre classification in automated ingest and appraisal metadata. In J. Gonzalo et al. Eds. Proceedings European Conf. on advanced technology and research in Digital Libraries, LNCS 4172, pages 63-74. Springer. DOI 10.1007/11863878 http://www.springerlink.com/content/2048x670g9863085/fulltext.pdf

Y. Kim and S.Ross, (2007) The Naming of Cats: Automated Genre Classification, The International Journal of Digital Curation, Vol 2 No 1, 2007. ISSN: 1746-8256
http://www.ijdc.net/./ijdc/article/view/24/27

Y. Kim and S. Ross (2007) Detecting Family Resemblance: Automated Genre Classification. CODATA Data Science Journal Vol 6, ISSN 1683-1470, S172-S183.
http://www.jstage.jst.go.jp/article/dsj/6/0/6_S172/_article

Y.Kim and B. Webber (2007) Implicit references to citations: a study of astronomy papers. presentation 20th International CODATA conference, preprint http://eprints.erpanet.org/127

Y. Kim and S.Ross (2007) Searching for Ground Truth: a Stepping Stone in Automated Genre Classification. In Thanos et al. Eds. Proceedings DELOS Conference on Digital Libraries, LNCS 4877, pages 248-261, Springer. DOI 10.1007/978-3-540-77088-6
http://www.springerlink.com/content/lt760613m2731723/fulltext.pdf

M. Dobreva, Y. Kim Y., S. Ross (2007) Metadata Extraction and Digital Preservation: an Overview. In: Second DELOS Conference on Digital Libraries, 5-7 December 2007, Tirrenia, Italy. http://tiny.cc/A6xqk

Y. Kim and S. Ross (2007) Variations of word frequencies in genre classification tasks. presentation DELOS conference on Digital Libraries, December, 2007, Tirrenia, Italy. preprint http://eprints.erpanet.org/134/

Y. Kim and S. Ross (2008) Examining Variations of Prominent Features in Genre Classification. In Proceedings 41st Hawaiian International Conference on System Sciences, IEEE Computer Society Press, ISBN-13:
978-0-7695-3075-8, ISBN-10: 0-7695-3075-3, ISSN 1530-1605.
http://tiny.cc/70iBM