{"id":"https://openalex.org/W2151684796","doi":"https://doi.org/10.1109/icdm.2003.1250930","title":"Statistical relational learning for document mining","display_name":"Statistical relational learning for document mining","publication_year":2004,"publication_date":"2004-04-23","ids":{"openalex":"https://openalex.org/W2151684796","doi":"https://doi.org/10.1109/icdm.2003.1250930","mag":"2151684796"},"language":"en","primary_location":{"id":"doi:10.1109/icdm.2003.1250930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.upenn.edu/bitstreams/ff5c3ade-acd5-458a-8bd8-a039741373aa/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027411355","display_name":"Alexandrin Popescul","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Popescul","raw_affiliation_strings":["Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044944954","display_name":"Lyle Ungar","orcid":"https://orcid.org/0000-0003-2047-1443"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L.H. Ungar","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA","NEC Laboratories of America, Inc., Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"NEC Laboratories of America, Inc., Princeton, NJ, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043733219","display_name":"Sandra Lawrence","orcid":"https://orcid.org/0000-0003-4429-869X"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Lawrence","raw_affiliation_strings":["Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110750330","display_name":"D.M. Pennock","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D.M. Pennock","raw_affiliation_strings":["NEC Laboratories of America, Inc., Princeton, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Laboratories of America, Inc., Princeton, NJ, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.8071,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.99164778,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9957000017166138,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9957000017166138,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9944000244140625,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9940000176429749,"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":0.7764584422111511},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5852145552635193},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5596874952316284},{"id":"https://openalex.org/keywords/inductive-logic-programming","display_name":"Inductive logic programming","score":0.5358453989028931},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.42788201570510864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3854261636734009},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38217276334762573},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38189446926116943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764584422111511},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5852145552635193},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5596874952316284},{"id":"https://openalex.org/C2779382394","wikidata":"https://www.wikidata.org/wiki/Q1464197","display_name":"Inductive logic programming","level":2,"score":0.5358453989028931},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.42788201570510864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3854261636734009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38217276334762573},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38189446926116943}],"mesh":[],"locations_count":10,"locations":[{"id":"doi:10.1109/icdm.2003.1250930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm.2003.1250930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE International Conference on Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.upenn.edu:cis_papers-1025","is_oa":true,"landing_page_url":"https://repository.upenn.edu/cis_papers/22","pdf_url":"https://repository.upenn.edu/bitstreams/ff5c3ade-acd5-458a-8bd8-a039741373aa/download","source":{"id":"https://openalex.org/S4306402083","display_name":"ScholarlyCommons (University of Pennsylvania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79576946","host_organization_name":"University of Pennsylvania","host_organization_lineage":["https://openalex.org/I79576946"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Departmental Papers (CIS)","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.12.6817","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.6817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/~popescul/Publications/statistical03icml.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.193.6111","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.193.6111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.iastate.edu/%7Ehonavar/srl-popescul.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.211.9691","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.211.9691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.biostat.wisc.edu/~page/popescul03dm.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.4907","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.4907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/~popescul/Publications/popescul03dm.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.426.829","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.426.829","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.469.4838","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.469.4838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.81.4482","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.81.4482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.upenn.edu/~popescul/Publications/popescul03dm.pdf","raw_type":"text"},{"id":"pmh:oai:repository.upenn.edu:20.500.14332/6256","is_oa":false,"landing_page_url":"https://repository.upenn.edu/handle/20.500.14332/6256","pdf_url":null,"source":{"id":"https://openalex.org/S4306402083","display_name":"ScholarlyCommons (University of Pennsylvania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79576946","host_organization_name":"University of Pennsylvania","host_organization_lineage":["https://openalex.org/I79576946"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"Presentation"}],"best_oa_location":{"id":"pmh:oai:repository.upenn.edu:cis_papers-1025","is_oa":true,"landing_page_url":"https://repository.upenn.edu/cis_papers/22","pdf_url":"https://repository.upenn.edu/bitstreams/ff5c3ade-acd5-458a-8bd8-a039741373aa/download","source":{"id":"https://openalex.org/S4306402083","display_name":"ScholarlyCommons (University of Pennsylvania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79576946","host_organization_name":"University of Pennsylvania","host_organization_lineage":["https://openalex.org/I79576946"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Departmental Papers (CIS)","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2151684796.pdf","grobid_xml":"https://content.openalex.org/works/W2151684796.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1482260847","https://openalex.org/W1487588218","https://openalex.org/W1490466294","https://openalex.org/W1498273559","https://openalex.org/W1509428113","https://openalex.org/W1514468887","https://openalex.org/W1522359868","https://openalex.org/W1541752891","https://openalex.org/W1545331097","https://openalex.org/W1571076699","https://openalex.org/W1592821781","https://openalex.org/W1608683810","https://openalex.org/W1619260253","https://openalex.org/W1666347389","https://openalex.org/W1769398419","https://openalex.org/W1791364091","https://openalex.org/W1814427248","https://openalex.org/W1971883645","https://openalex.org/W1973948212","https://openalex.org/W2007395264","https://openalex.org/W2033072307","https://openalex.org/W2045373010","https://openalex.org/W2058815839","https://openalex.org/W2076008912","https://openalex.org/W2078029048","https://openalex.org/W2097915776","https://openalex.org/W2101005742","https://openalex.org/W2108346334","https://openalex.org/W2113243831","https://openalex.org/W2121250409","https://openalex.org/W2126185296","https://openalex.org/W2138745909","https://openalex.org/W2147880316","https://openalex.org/W2154498027","https://openalex.org/W2155800811","https://openalex.org/W2155925463","https://openalex.org/W2161349318","https://openalex.org/W2168175751","https://openalex.org/W2283350629","https://openalex.org/W2396715201","https://openalex.org/W2962735828","https://openalex.org/W2982977987","https://openalex.org/W3015720892","https://openalex.org/W3020831056","https://openalex.org/W3149838063","https://openalex.org/W6636434499","https://openalex.org/W6637194779","https://openalex.org/W6637886241","https://openalex.org/W6665272994","https://openalex.org/W6674856645","https://openalex.org/W6676036752","https://openalex.org/W6678161993","https://openalex.org/W6680642335","https://openalex.org/W6695666202","https://openalex.org/W6711916277"],"related_works":["https://openalex.org/W2978856588","https://openalex.org/W1558569658","https://openalex.org/W1501498539","https://openalex.org/W2953272728","https://openalex.org/W320292658","https://openalex.org/W1523236614","https://openalex.org/W2001007279","https://openalex.org/W2596625410","https://openalex.org/W3181676408","https://openalex.org/W2079674650"],"abstract_inverted_index":{"A":[0],"major":[1],"obstacle":[2],"to":[3,36,69,74,100,108,146,160,163],"fully":[4],"integrated":[5,34,91],"deployment":[6],"of":[7,65,78,124],"many":[8,81],"data":[9,16,135],"mining":[10],"algorithms":[11],"is":[12],"the":[13,44,71,101,122],"assumption":[14],"that":[15],"sits":[17],"in":[18,55,113,142],"a":[19,93,114],"single":[20,94],"table,":[21],"even":[22],"though":[23],"most":[24],"real-world":[25],"databases":[26],"have":[27],"complex":[28],"relational":[29,40,134],"structures.":[30],"We":[31,42,117],"propose":[32],"an":[33],"approach":[35,140],"statistical":[37,102],"modelling":[38],"from":[39,137],"databases.":[41],"structure":[43],"search":[45,72],"space":[46,73],"based":[47,132],"on":[48,133],"\"refinement":[49],"graphs\",":[50],"which":[51,82],"are":[52,83,90],"widely":[53],"used":[54,159],"inductive":[56],"logic":[57,61],"programming":[58],"for":[59,104,121],"learning":[60],"descriptions.":[62],"The":[63,154],"use":[64],"statistics":[66],"allows":[67],"us":[68],"extend":[70],"include":[75],"richer":[76],"set":[77],"features,":[79],"including":[80],"not":[84],"Boolean.":[85],"Search":[86],"and":[87],"model":[88],"selection":[89,111],"into":[92],"process,":[95],"allowing":[96],"information":[97],"criteria":[98],"native":[99],"model,":[103],"example":[105],"logistic":[106],"regression,":[107],"make":[109],"feature":[110],"decisions":[112],"step-wise":[115],"manner.":[116],"present":[118],"experimental":[119],"results":[120,141],"task":[123],"predicting":[125],"where":[126,162],"scientific":[127],"papers":[128],"will":[129],"be":[130,158],"published":[131],"taken":[136],"CiteSeer.":[138],"Our":[139],"classification":[143],"accuracies":[144],"superior":[145],"those":[147],"achieved":[148],"when":[149],"using":[150],"classical":[151],"\"flat\"":[152],"features.":[153],"resulting":[155],"classifier":[156],"can":[157],"recommend":[161],"publish":[164],"articles.":[165]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}