{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T10:40:09Z","timestamp":1770288009703,"version":"3.49.0"},"reference-count":33,"publisher":"IEEE Comput. Soc","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/jcdl.2003.1204842","type":"proceedings-article","created":{"date-parts":[[2004,1,23]],"date-time":"2004-01-23T23:33:03Z","timestamp":1074900783000},"page":"37-48","source":"Crossref","is-referenced-by-count":89,"title":["Automatic document metadata extraction using support vector machines"],"prefix":"10.1109","author":[{"family":"Hui Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.L.","family":"Giles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E.","family":"Manavoglu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Hongyuan Zha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Zhenyue Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E.A.","family":"Fox","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/564396.564398"},{"key":"ref32","first-page":"412","article-title":"A comparative study on feature selection in text categorization","author":"yang","year":"1997","journal-title":"Proceedings of ICML-97 14th International Conference on Machine Learning"},{"key":"ref31","first-page":"117","article-title":"The Dublin Core: A simple content description format for electronic resources","volume":"40","author":"weibel","year":"1999","journal-title":"NFAIS Newsletter"},{"key":"ref30","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref10","article-title":"Identity uncertainty and citation matching","author":"pasula","year":"2002","journal-title":"Proc of the Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref11","article-title":"Making large-scale Support Vector Machine learning practical","author":"joachims","year":"1998","journal-title":"Advances in Kernel Methods Support Vector Machines"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/383952.383974"},{"key":"ref13","article-title":"OAI Harvester Crawling Status","author":"kent","year":"2001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/544414.544493"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/1117601.1117635"},{"key":"ref16","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"Proc 18th International Conf on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/2.769447"},{"key":"ref18","article-title":"Federating heterogeneous Digital Libraries by meta-data harvesting","author":"liu","year":"2002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/276675.276693"},{"key":"ref28","article-title":"The power of word clusters for text classification","author":"slonim","year":"2001","journal-title":"Proc 23rd European Colloquium on Information Retrieval Research (ECIR)"},{"key":"ref4","article-title":"Celestial &#x2013; Open Archives Gateway","author":"brody","year":"2002"},{"key":"ref27","first-page":"37","article-title":"Learning hidden Markov model structure for information extraction","author":"seymore","year":"1999","journal-title":"Proc of AAAI 99 Workshop on Machine Learning for Information Extraction"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0501-34"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511801389"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1118853.1118882"},{"key":"ref5","first-page":"786","article-title":"A maximum entropy approach to information extraction from semi-structured and free text","author":"chieu","year":"2002","journal-title":"Proc of the 18th National Conference on Artificial Intelligence (AAAI-2002)"},{"key":"ref8","article-title":"A divisive information theoretic feature clustering for text classification","author":"dhillon","year":"2002","journal-title":"J Machine Learning Research (JMLR)"},{"key":"ref7","article-title":"The Open Archives Initiative Protocol for Metadata Harvesting","author":"de sompel","year":"2001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/290941.290970"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/288627.288651"},{"key":"ref1","year":"2002","journal-title":"The World Factbook"},{"key":"ref20","first-page":"591","article-title":"Maximum entropy Markov models for information extraction and segmentation","author":"mccallum","year":"2000","journal-title":"Proc 17th International Conf on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3115\/1118853.1118873"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009953814988"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL.2003.1204864"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/273035.273044"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.3115\/1073336.1073360","article-title":"Knowlege-free induction of inflectional morphologies","author":"schone","year":"2001","journal-title":"Proceedings of North American Chapter of the Association for Computational Linguistics (NAACL)"},{"key":"ref25","first-page":"82","article-title":"Text chunking using transformation-based learning","author":"ramshaw","year":"1995","journal-title":"Proc Workshop on Very Large Corpora"}],"event":{"name":"2003 Joint Conference on Digital Libraries","location":"Houston, TX, USA","acronym":"JCDL-03"},"container-title":["2003 Joint Conference on Digital Libraries, 2003. Proceedings."],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8569\/27127\/01204842.pdf?arnumber=1204842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,15]],"date-time":"2017-06-15T23:18:16Z","timestamp":1497568696000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1204842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/jcdl.2003.1204842","relation":{},"subject":[]}}