{"id":"https://openalex.org/W2101486006","doi":"https://doi.org/10.1109/tai.1993.633991","title":"A tool for classifying office documents","display_name":"A tool for classifying office documents","publication_year":2002,"publication_date":"2002-12-30","ids":{"openalex":"https://openalex.org/W2101486006","doi":"https://doi.org/10.1109/tai.1993.633991","mag":"2101486006"},"language":"en","primary_location":{"id":"doi:10.1109/tai.1993.633991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.1993.633991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 1993 IEEE Conference on Tools with Al (TAI-93)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032921642","display_name":"Xiaolong Hao","orcid":"https://orcid.org/0000-0001-5452-3016"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"X. Hao","raw_affiliation_strings":["Institute for Integrated Systems Research, Department of Computer and Information Science, New Jersey Institute of Technology, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Integrated Systems Research, Department of Computer and Information Science, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060438603","display_name":"J. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Wang","raw_affiliation_strings":["Institute for Integrated Systems Research Department of Computer and Information Science, New Jersey Institute of Technology, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Integrated Systems Research Department of Computer and Information Science, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071607128","display_name":"Michael Bieber","orcid":"https://orcid.org/0000-0002-5535-6480"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Bieber","raw_affiliation_strings":["Institute Systefor Integrated ms Research Department of Computer and Information Science, New Jersey Institute of Technology, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Institute Systefor Integrated ms Research Department of Computer and Information Science, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048050128","display_name":"Peter A. Ng","orcid":"https://orcid.org/0000-0001-8509-5544"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Ng","raw_affiliation_strings":["Institute Systefor Integrated ms Research Department of Computer and Information Science, New Jersey Institute of Technology, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Institute Systefor Integrated ms Research Department of Computer and Information Science, New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032921642"],"corresponding_institution_ids":["https://openalex.org/I118118575"],"apc_list":null,"apc_paid":null,"fwci":0.2313,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.5063088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"427","last_page":"434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.8223915100097656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8019131422042847},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6287117600440979},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6152018308639526},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6103264689445496},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5349812507629395},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4789467453956604},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45756796002388},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.4299783706665039},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.42536163330078125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37947314977645874},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.18396714329719543},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10363119840621948},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08767300844192505}],"concepts":[{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.8223915100097656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019131422042847},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6287117600440979},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6152018308639526},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6103264689445496},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5349812507629395},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4789467453956604},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45756796002388},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.4299783706665039},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.42536163330078125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37947314977645874},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.18396714329719543},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10363119840621948},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08767300844192505},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.1993.633991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.1993.633991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 1993 IEEE Conference on Tools with Al (TAI-93)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W14494209","https://openalex.org/W1946662921","https://openalex.org/W1967118885","https://openalex.org/W2004162112","https://openalex.org/W2006299591","https://openalex.org/W2039135287","https://openalex.org/W2082183672","https://openalex.org/W2095926335","https://openalex.org/W2114660801","https://openalex.org/W2119496217","https://openalex.org/W2127021241","https://openalex.org/W2145805921","https://openalex.org/W2157307495","https://openalex.org/W4238415164","https://openalex.org/W6600560206","https://openalex.org/W6681510727"],"related_works":["https://openalex.org/W2071459461","https://openalex.org/W2093885745","https://openalex.org/W2351266481","https://openalex.org/W2132547887","https://openalex.org/W2516987005","https://openalex.org/W2907786475","https://openalex.org/W2963447120","https://openalex.org/W4289082820","https://openalex.org/W2092152400","https://openalex.org/W2963196945"],"abstract_inverted_index":{"The":[0,35,61,92],"authors":[1],"present":[2],"the":[3,24,67,82,88,97,114],"design":[4],"of":[5,84,101,105],"a":[6,14,31,38,74],"tool":[7,36,98],"for":[8,41],"classifying":[9,102],"office":[10,106],"documents.":[11],"They":[12],"represent":[13],"document's":[15],"layout":[16,25],"structure":[17,26],"using":[18,73],"an":[19],"ordered":[20],"labeled":[21],"tree,":[22],"called":[23],"tree":[27],"(L-S-tree),":[28],"based":[29],"on":[30],"nested":[32],"segmentation":[33],"procedure.":[34],"uses":[37],"sample-based":[39],"approach":[40],"learning,":[42],"where":[43],"concepts":[44],"are":[45,53],"learned":[46],"by":[47,55],"retaining":[48],"samples":[49,112],"and":[50,80,90],"new":[51],"documents":[52,89],"classified":[54],"matching":[56,62,78],"their":[57],"L-S-trees":[58],"with":[59,109],"samples.":[60,91],"process":[63],"involves":[64],"both":[65],"computing":[66],"edit":[68],"distance":[69],"between":[70,87],"two":[71],"trees":[72],"previously":[75],"developed":[76],"pattern":[77],"toolkit,":[79],"calculating":[81],"degree":[83],"conceptual":[85],"closeness":[86],"experimental":[93],"results":[94],"show":[95],"that":[96],"is":[99],"capable":[100],"various":[103],"types":[104],"documents,":[107],"even":[108],"very":[110],"few":[111],"in":[113],"sample":[115],"base.":[116]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
