{"id":"https://openalex.org/W2102337021","doi":"https://doi.org/10.14778/1687627.1687667","title":"Stop word and related problems in web interface integration","display_name":"Stop word and related problems in web interface integration","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2102337021","doi":"https://doi.org/10.14778/1687627.1687667","mag":"2102337021"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687667","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687667","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/A5057346703","display_name":"Eduard Dragut","orcid":"https://orcid.org/0000-0002-3103-054X"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eduard Dragut","raw_affiliation_strings":["University of Illinois at Chicago"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386863","display_name":"Fang Fang","orcid":"https://orcid.org/0000-0002-5445-0766"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fang Fang","raw_affiliation_strings":["University of Illinois at Chicago"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088870605","display_name":"Prasad Sistla","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasad Sistla","raw_affiliation_strings":["University of Illinois at Chicago"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109181755","display_name":"Clement Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clement Yu","raw_affiliation_strings":["University of Illinois at Chicago"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101960531","display_name":"Weiyi Meng","orcid":"https://orcid.org/0000-0002-7246-2058"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiyi Meng","raw_affiliation_strings":["SUNY at Binghamton"],"affiliations":[{"raw_affiliation_string":"SUNY at Binghamton","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057346703"],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":null,"apc_paid":null,"fwci":8.5597,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.97700197,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"349","last_page":"360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9990000128746033,"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":0.8109152317047119},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.7613959312438965},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6498857140541077},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6099557876586914},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5923115015029907},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5031566023826599},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49540412425994873},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.49058976769447327},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4710262715816498},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.43324533104896545},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3563374876976013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3254261314868927},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.2009091079235077},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.19433975219726562},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10433730483055115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109152317047119},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.7613959312438965},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6498857140541077},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6099557876586914},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5923115015029907},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5031566023826599},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49540412425994873},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.49058976769447327},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4710262715816498},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.43324533104896545},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3563374876976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3254261314868927},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2009091079235077},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.19433975219726562},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10433730483055115},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"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/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/1687627.1687667","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687667","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"},{"id":"pmh:oai:docs.lib.purdue.edu:ccpubs-1164","is_oa":false,"landing_page_url":"https://docs.lib.purdue.edu/ccpubs/154","pdf_url":null,"source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cyber Center Publications","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.6934","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.6934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/2/vldb09-384.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W144740258","https://openalex.org/W175554243","https://openalex.org/W343945789","https://openalex.org/W1534024124","https://openalex.org/W1660390307","https://openalex.org/W1985079777","https://openalex.org/W2008896880","https://openalex.org/W2036373663","https://openalex.org/W2068737686","https://openalex.org/W2071718761","https://openalex.org/W2098016092","https://openalex.org/W2100377551","https://openalex.org/W2100935296","https://openalex.org/W2108489852","https://openalex.org/W2117058208","https://openalex.org/W2117078075","https://openalex.org/W2134007343","https://openalex.org/W2139259611","https://openalex.org/W2141461755","https://openalex.org/W2143607396","https://openalex.org/W2149342630","https://openalex.org/W2149393279","https://openalex.org/W2156543375","https://openalex.org/W2157060173","https://openalex.org/W2160587453","https://openalex.org/W2161443453","https://openalex.org/W2164896748","https://openalex.org/W2165897980","https://openalex.org/W2166776180","https://openalex.org/W2171970775","https://openalex.org/W2490605817","https://openalex.org/W4235505822","https://openalex.org/W4255198209","https://openalex.org/W6607064022","https://openalex.org/W6637101025"],"related_works":["https://openalex.org/W2471940468","https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W4226075635","https://openalex.org/W1528218860","https://openalex.org/W2386242059","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W2029826694","https://openalex.org/W2159303222"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,20,43,68,75,144,164,211],"recent":[3],"research":[4],"projects":[5],"on":[6,88,150],"integrating":[7],"Web":[8,202],"databases":[9],"has":[10],"been":[11],"to":[12,16,51,174],"enable":[13],"uniform":[14],"access":[15],"the":[17,26,66,90,125,142,201],"large":[18],"amount":[19],"data":[21,199],"behind":[22],"query":[23,32],"interfaces.":[24],"Among":[25],"tasks":[27,44,62],"addressed":[28],"are:":[29],"source":[30],"discovery,":[31],"interface":[33],"extraction,":[34],"schema":[35],"matching,":[36],"etc.":[37],"There":[38],"are":[39,46],"also":[40],"a":[41,85,99,104,112,162,171],"number":[42],"that":[45],"commonly":[47],"ignored":[48],"or":[49,57],"assumed":[50],"be":[52],"apriori":[53],"solved":[54],"either":[55],"manually":[56],"by":[58],"some":[59],"oracle.":[60],"These":[61,81],"include":[63],"(1)":[64],"finding":[65],"set":[67],"stop":[69,105,126],"words":[70,145],"and":[71,92,120,133,148,159,190,194],"(2)":[72],"handling":[73],"occurrences":[74],"\"semantic":[76],"enrichment":[77],"words\"":[78],"within":[79],"labels.":[80,96],"two":[82],"subproblems":[83],"have":[84],"direct":[86],"impact":[87,143],"determining":[89],"synonymy":[91,176],"hyponymy":[93,179],"relationships":[94,153],"between":[95,154],"In":[97,138,167],"(1),":[98],"word":[100,106,114,127],"like":[101,146],"\"from\"":[102],"is":[103,111,161],"in":[107,115,203,215],"general":[108],"but":[109],"it":[110],"content":[113],"domains":[116],"such":[117],"as":[118],"Airline":[119],"Real":[121],"Estate.":[122],"We":[123,186,196,206],"formulate":[124],"problem":[128],",":[129],"prove":[130],"its":[131,188],"complexity":[132],"provide":[134],"an":[135],"approximation":[136],"algorithm.":[137],"(2),":[139],"we":[140,169],"study":[141],"AND":[147],"OR":[149],"establishing":[151],"semantic":[152],"labels":[155,182,210],"(e.g.":[156],"\"departure":[157,165],"date":[158],"time\"":[160],"hypernym":[163],"date\").":[166],"addition,":[168],"develop":[170],"theoretical":[172],"framework":[173],"differentiate":[175],"relationship":[177,180],"from":[178,200],"among":[181],"involving":[183],"multiple":[184],"words.":[185],"scrutinize":[187],"strength":[189],"limitations":[191],"both":[192],"analytically":[193],"experimentally.":[195],"use":[197],"real":[198],"our":[204],"experiments.":[205],"analyze":[207],"over":[208],"2300":[209],"220":[212],"user":[213],"interfaces":[214],"9":[216],"distinct":[217],"domains.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}