Automatic document metadata extraction using support vector machines

Hui Han, C. L. Giles, E. Manavoglu, Hongyuan Zha, Zhenyue Zhang, E. A. Fox

Research output: Chapter in Book/Report/Conference proceedingConference contribution

243 Scopus citations


Automatic metadata generation provides scalability and usability for digital libraries and their collections. Machine learning methods offer robust and adaptable automatic metadata extraction. We describe a support vector machine classification-based method for metadata extraction from header part of research papers and show that it outperforms other machine learning methods on the same task. The method first classifies each line of the header into one or more of 15 classes. An iterative convergence procedure is then used to improve the line classification by using the predicted class labels of its neighbor lines in the previous round. Further metadata extraction is done by seeking the best chunk boundaries of each line. We found that discovery and use of the structural patterns of the data and domain based word clustering can improve the metadata extraction performance. An appropriate feature normalization also greatly improves the classification performance. Our metadata extraction method was originally designed to improve the metadata extraction quality of the digital libraries Citeseer [S. Lawrence et al., (1999)] and EbizSearch [Y. Petinot et al., (2003)]. We believe it can be generalized to other digital libraries.

Original languageEnglish (US)
Title of host publicationProceedings - 2003 Joint Conference on Digital Libraries, JCDL 2003
EditorsLois Delcambre, Geneva Henry, Catherine C. Marshall
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages12
ISBN (Electronic)0769519393
StatePublished - 2003
Event2003 Joint Conference on Digital Libraries, JCDL 2003 - Houston, United States
Duration: May 27 2003May 31 2003

Publication series

NameProceedings of the ACM/IEEE Joint Conference on Digital Libraries
ISSN (Print)1552-5996


Other2003 Joint Conference on Digital Libraries, JCDL 2003
Country/TerritoryUnited States

All Science Journal Classification (ASJC) codes

  • General Engineering


Dive into the research topics of 'Automatic document metadata extraction using support vector machines'. Together they form a unique fingerprint.

Cite this