{"id":"https://openalex.org/W2107068745","doi":"https://doi.org/10.1145/1066677.1066917","title":"Rule-based word clustering for document metadata extraction","display_name":"Rule-based word clustering for document metadata extraction","publication_year":2005,"publication_date":"2005-03-13","ids":{"openalex":"https://openalex.org/W2107068745","doi":"https://doi.org/10.1145/1066677.1066917","mag":"2107068745"},"language":"en","primary_location":{"id":"doi:10.1145/1066677.1066917","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066677.1066917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM symposium on Applied computing","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/A5103090601","display_name":"Hui Han","orcid":"https://orcid.org/0009-0000-2103-3782"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hui Han","raw_affiliation_strings":["Yahoo Inc., Sunnyvale, CA","Yahoo! Inc., Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Yahoo Inc., Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Inc., Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079433953","display_name":"Eren Manavoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eren Manavoglu","raw_affiliation_strings":["The Pennsylvania State University, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046703129","display_name":"Hongyuan Zha","orcid":"https://orcid.org/0000-0001-7493-0911"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyuan Zha","raw_affiliation_strings":["The Pennsylvania State University, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070966667","display_name":"Kostas Tsioutsiouliklis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kostas Tsioutsiouliklis","raw_affiliation_strings":["Yahoo Inc., Sunnyvale, CA","Yahoo! Inc., Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Yahoo Inc., Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Inc., Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["The Pennsylvania State University, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101503267","display_name":"Xiangmin Zhang","orcid":"https://orcid.org/0000-0001-5479-6671"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangmin Zhang","raw_affiliation_strings":["Rutgers University, New Brunswick, NJ"],"affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, NJ","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103090601"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":3.6536,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.93177332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1049","last_page":"1053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8101436495780945},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6920157074928284},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6588497161865234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6278139352798462},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5689390897750854},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5300155878067017},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.522271454334259},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.49751999974250793},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4723535478115082},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.451900452375412},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4343823492527008},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.4336872696876526},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.4222482442855835},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39867138862609863},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35053884983062744},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13515233993530273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101436495780945},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6920157074928284},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6588497161865234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6278139352798462},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5689390897750854},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5300155878067017},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.522271454334259},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.49751999974250793},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4723535478115082},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.451900452375412},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4343823492527008},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.4336872696876526},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.4222482442855835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39867138862609863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35053884983062744},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13515233993530273},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1066677.1066917","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1066677.1066917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2005 ACM symposium on Applied computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.94.2944","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.94.2944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://clgiles.ist.psu.edu/papers/SAC-2005-Document-Metadata-Extraction.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W206794860","https://openalex.org/W1568339100","https://openalex.org/W1583837637","https://openalex.org/W1595613095","https://openalex.org/W1612003148","https://openalex.org/W1983311927","https://openalex.org/W2064580901","https://openalex.org/W2103986443","https://openalex.org/W2115023510","https://openalex.org/W2125838338","https://openalex.org/W2127314673","https://openalex.org/W2138570191","https://openalex.org/W2140479099","https://openalex.org/W2145130412","https://openalex.org/W2147152072","https://openalex.org/W2156909104","https://openalex.org/W2162630660","https://openalex.org/W2163918411","https://openalex.org/W2167075392","https://openalex.org/W2435251607","https://openalex.org/W2531563875","https://openalex.org/W6635548358","https://openalex.org/W6636440780"],"related_works":["https://openalex.org/W2988584621","https://openalex.org/W4240717064","https://openalex.org/W4214728210","https://openalex.org/W58628767","https://openalex.org/W2611282738","https://openalex.org/W3006526473","https://openalex.org/W167782738","https://openalex.org/W1573371033","https://openalex.org/W4387951040","https://openalex.org/W2035503345"],"abstract_inverted_index":{"Text":[0,25],"classification":[1,20,26,65,109],"is":[2,51],"still":[3],"an":[4,52],"important":[5],"problem":[6],"for":[7,22,76],"unlabeled":[8],"text;":[9],"CiteSeer,":[10],"a":[11,28,70,102,116],"computer":[12],"science":[13],"document":[14,23,112,153],"search":[15],"engine,":[16],"uses":[17,27],"automatic":[18],"text":[19,31,64,138],"methods":[21],"indexing.":[24],"document's":[29],"original":[30,137],"words":[32],"as":[33],"the":[34,89,121,136,145,150],"primary":[35],"feature":[36,47,57,60,78,99,131],"representation.":[37,79],"However,":[38],"such":[39,97],"representation":[40,132],"usually":[41],"comes":[42],"with":[43],"high":[44],"dimensionality":[45,58,95],"and":[46,59,62,88,115],"sparseness.":[48],"Word":[49],"clustering":[50,74,142,148],"effective":[53],"approach":[54],"to":[55,130],"reduce":[56],"sparseness,":[61],"improve":[63],"performance.":[66],"This":[67],"paper":[68],"introduces":[69],"domain":[71,86],"Rule-based":[72],"word":[73,90,141,147],"method":[75],"cluster":[77,98],"The":[80],"clusters":[81],"are":[82],"formed":[83],"from":[84],"various":[85],"databases":[87],"orthographic":[91],"properties.":[92],"Besides":[93],"significant":[94],"reduction,":[96],"representations":[100],"show":[101],"6.6%":[103],"absolute":[104,118],"improvement":[105,119],"on":[106,108,120,135],"average":[107],"performance":[110],"of":[111,124,152],"header":[113],"lines":[114],"8.4%":[117],"overall":[122],"accuracy":[123],"bibliographic":[125],"fields":[126],"extraction,":[127],"in":[128,149],"contrast":[129],"just":[133],"based":[134],"words.":[139],"Our":[140],"even":[143],"outperforms":[144],"distributional":[146],"context":[151],"metadata":[154],"extraction.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}