{"id":"https://openalex.org/W2145007893","doi":"https://doi.org/10.14778/1687627.1687661","title":"Answering table augmentation queries from unstructured lists on the web","display_name":"Answering table augmentation queries from unstructured lists on the web","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2145007893","doi":"https://doi.org/10.14778/1687627.1687661","mag":"2145007893"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687661","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687661","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/A5075937808","display_name":"Rahul Gupta","orcid":"https://orcid.org/0000-0002-9277-3718"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Rahul Gupta","raw_affiliation_strings":["IIT Bombay, India","IIT Bombay, INDIA#TAB#"],"affiliations":[{"raw_affiliation_string":"IIT Bombay, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"IIT Bombay, INDIA#TAB#","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031035935","display_name":"Sunita Sarawagi","orcid":"https://orcid.org/0009-0005-9538-6616"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunita Sarawagi","raw_affiliation_strings":["IIT Bombay, India","IIT Bombay, INDIA#TAB#"],"affiliations":[{"raw_affiliation_string":"IIT Bombay, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"IIT Bombay, INDIA#TAB#","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075937808"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":27.1706,"has_fulltext":false,"cited_by_count":108,"citation_normalized_percentile":{"value":0.99460128,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"2","issue":"1","first_page":"289","last_page":"300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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/T11719","display_name":"Data Quality and Management","score":0.9975000023841858,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9897000193595886,"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":0.8429674506187439},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.8306402564048767},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6701456904411316},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6315998435020447},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.44611576199531555},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4334322214126587},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36463814973831177},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.28002917766571045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429674506187439},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.8306402564048767},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6701456904411316},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6315998435020447},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.44611576199531555},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4334322214126587},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36463814973831177},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.28002917766571045}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/1687627.1687661","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687661","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:CiteSeerX.psu:10.1.1.592.3929","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.592.3929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.it.iitb.ac.in/~sunita/papers/vldb09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W197270748","https://openalex.org/W1691409177","https://openalex.org/W1761401273","https://openalex.org/W1990061958","https://openalex.org/W2022158118","https://openalex.org/W2057052429","https://openalex.org/W2067566391","https://openalex.org/W2092819480","https://openalex.org/W2093559286","https://openalex.org/W2105423800","https://openalex.org/W2110219039","https://openalex.org/W2117510361","https://openalex.org/W2124410446","https://openalex.org/W2135223301","https://openalex.org/W2135767707","https://openalex.org/W2140602286","https://openalex.org/W2143309843","https://openalex.org/W2158188757","https://openalex.org/W2159491434","https://openalex.org/W2160196229","https://openalex.org/W2171472464","https://openalex.org/W2293997450","https://openalex.org/W2913389685","https://openalex.org/W6680646450","https://openalex.org/W6697127918"],"related_works":["https://openalex.org/W4281971614","https://openalex.org/W4226523698","https://openalex.org/W2131131934","https://openalex.org/W1519332147","https://openalex.org/W4206785508","https://openalex.org/W4385281412","https://openalex.org/W2726157743","https://openalex.org/W2070384782","https://openalex.org/W2414530304","https://openalex.org/W3122529031"],"abstract_inverted_index":{"We":[0,29,138],"present":[1,147],"the":[2,18,27,40,51,62,67,70,79,93,95,104,132],"design":[3],"of":[4,21,57,115,125,136,158,197],"a":[5,9,12,31,54,74,85,194],"system":[6,185],"for":[7],"assembling":[8],"table":[10],"from":[11,53,81,118],"few":[13,120],"example":[14],"rows":[15,43,117],"by":[16,99],"harnessing":[17],"huge":[19],"corpus":[20],"information-rich":[22],"but":[23],"unstructured":[24,174],"lists":[25,48,83,129,175],"on":[26],"web.":[28],"developed":[30],"totally":[32],"unsupervised":[33],"end":[34,36],"to":[35,50,69,92,141],"approach":[37],"which":[38],"given":[39],"sample":[41,182],"query":[42,52,71],"---":[44],"(a)":[45],"retrieves":[46],"HTML":[47],"relevant":[49],"pre-indexed":[55],"crawl":[56],"web":[58],"lists,":[59],"(b)":[60],"segments":[61,68],"list":[63],"records":[64,97],"and":[65,90,122,127,134,146,150,171],"maps":[66],"schema":[72,160],"using":[73],"statistical":[75,142],"model,":[76],"(c)":[77],"consolidates":[78],"results":[80],"multiple":[82],"into":[84],"unified":[86],"merged":[87],"table,":[88],"(d)":[89],"presents":[91],"user":[94],"consolidated":[96],"ranked":[98],"their":[100],"estimated":[101],"membership":[102],"in":[103,110],"target":[105,169],"relation.":[106],"The":[107],"key":[108],"challenges":[109],"this":[111],"task":[112],"include":[113],"construction":[114],"new":[116],"very":[119,187],"examples,":[121],"an":[123],"abundance":[124],"noisy":[126],"irrelevant":[128],"that":[130,153,177],"swamp":[131],"consolidation":[133,149],"ranking":[135,151],"rows.":[137],"propose":[139],"modifications":[140],"record":[143],"segmentation":[144],"models,":[145],"novel":[148],"techniques":[152],"can":[154],"process":[155],"input":[156],"tables":[157,170],"arbitrary":[159],"without":[161],"requiring":[162],"any":[163],"human":[164],"supervision.":[165],"Experiments":[166],"with":[167,179,193],"Wikipedia":[168,191],"16":[172],"million":[173],"show":[176],"even":[178],"just":[180],"three":[181],"rows,":[183],"our":[184],"is":[186],"effective":[188],"at":[189],"recreating":[190],"tables,":[192],"mean":[195],"runtime":[196],"around":[198],"20s.":[199]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":14}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}