{"id":"https://openalex.org/W1999563429","doi":"https://doi.org/10.14778/1920841.1920916","title":"Automatic rule refinement for information extraction","display_name":"Automatic rule refinement for information extraction","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W1999563429","doi":"https://doi.org/10.14778/1920841.1920916","mag":"1999563429"},"language":"en","primary_location":{"id":"doi:10.14778/1920841.1920916","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920916","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5100395501","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0002-5043-7652"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["University of Michigan","(University of Michigan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"(University of Michigan)","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050310059","display_name":"Laura Chiticariu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura Chiticariu","raw_affiliation_strings":["IBM Research - Almaden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079463431","display_name":"Vivian S. Chu","orcid":"https://orcid.org/0000-0002-0304-3650"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivian Chu","raw_affiliation_strings":["IBM Research - Almaden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087012731","display_name":"H. V. Jagadish","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. V. Jagadish","raw_affiliation_strings":["University of Michigan","(University of Michigan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"(University of Michigan)","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074416632","display_name":"Frederick Reiss","orcid":"https://orcid.org/0009-0002-1254-1798"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frederick R. Reiss","raw_affiliation_strings":["IBM Research - Almaden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Almaden","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.0351,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.98591964,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"3","issue":"1-2","first_page":"588","last_page":"597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9922999739646912,"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":0.8298434019088745},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6642938852310181},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6139395236968994},{"id":"https://openalex.org/keywords/rule-based-system","display_name":"Rule-based system","score":0.5896427631378174},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5748586654663086},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.529163122177124},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.5117949843406677},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.486270546913147},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.46176499128341675},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.389152467250824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2182464897632599},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1796148717403412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8298434019088745},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6642938852310181},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6139395236968994},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.5896427631378174},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5748586654663086},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.529163122177124},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.5117949843406677},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.486270546913147},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.46176499128341675},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.389152467250824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2182464897632599},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1796148717403412},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1920841.1920916","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920916","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W10455613","https://openalex.org/W1534730506","https://openalex.org/W1547214099","https://openalex.org/W1563062065","https://openalex.org/W1563635790","https://openalex.org/W1969595233","https://openalex.org/W2009591769","https://openalex.org/W2020270115","https://openalex.org/W2035266017","https://openalex.org/W2048372226","https://openalex.org/W2054967933","https://openalex.org/W2060164640","https://openalex.org/W2098720114","https://openalex.org/W2103931177","https://openalex.org/W2106950427","https://openalex.org/W2110367654","https://openalex.org/W2114663556","https://openalex.org/W2119325664","https://openalex.org/W2136856075","https://openalex.org/W2144416276","https://openalex.org/W2144578941","https://openalex.org/W2146191280","https://openalex.org/W2147880316","https://openalex.org/W2149099978","https://openalex.org/W2156454791","https://openalex.org/W2164949130","https://openalex.org/W2166709576","https://openalex.org/W2167541073","https://openalex.org/W2168561231","https://openalex.org/W2293299776","https://openalex.org/W2432471317","https://openalex.org/W4246215794"],"related_works":["https://openalex.org/W1788528807","https://openalex.org/W2725657302","https://openalex.org/W2393978999","https://openalex.org/W2153799433","https://openalex.org/W2367301249","https://openalex.org/W2379157006","https://openalex.org/W2352337653","https://openalex.org/W3036744775","https://openalex.org/W2559989503","https://openalex.org/W2151861426"],"abstract_inverted_index":{"Rule-based":[0],"information":[1,23,112],"extraction":[2,24,77,113],"from":[3],"text":[4],"is":[5,32],"increasingly":[6],"being":[7],"used":[8],"to":[9,13,33,54,67,90],"populate":[10],"databases":[11],"and":[12,29,79,81,121],"support":[14],"structured":[15],"queries":[16],"on":[17],"unstructured":[18],"text.":[19],"Specification":[20],"of":[21,51,58,76,95],"suitable":[22],"rules":[25,35,78],"requires":[26],"considerable":[27],"skill":[28],"standard":[30],"practice":[31],"refine":[34],"iteratively,":[36],"with":[37],"substantial":[38],"effort.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,85],"show":[44],"that":[45,98],"techniques":[46],"developed":[47,87,115],"in":[48,61,69,109],"the":[49,56,110],"context":[50],"data":[52],"provenance,":[53],"determine":[55],"lineage":[57],"a":[59,62,74,88,92],"tuple":[60],"database,":[63],"can":[64,103],"be":[65],"leveraged":[66],"assist":[68],"rule":[70,96,101],"refinement.":[71],"Specifically,":[72],"given":[73],"set":[75],"correct":[80],"incorrect":[82],"extracted":[83],"data,":[84],"have":[86],"technique":[89,108],"suggest":[91],"ranked":[93],"list":[94],"modifications":[97],"an":[99],"expert":[100],"specifier":[102],"consider.":[104],"We":[105],"implemented":[106],"our":[107],"SystemT":[111],"system":[114],"at":[116],"IBM":[117],"Research":[118],"--":[119],"Almaden":[120],"experimentally":[122],"demonstrate":[123],"its":[124],"effectiveness.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
