{"id":"https://openalex.org/W4410636879","doi":"https://doi.org/10.1145/3701716.3715600","title":"WebTableX: Efficiently Discovering Web Table Transformations Through Sampling","display_name":"WebTableX: Efficiently Discovering Web Table Transformations Through Sampling","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636879","doi":"https://doi.org/10.1145/3701716.3715600"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3715600","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715600","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715600","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715600","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045831058","display_name":"Soroush Omidvar Tehrani","orcid":"https://orcid.org/0000-0002-3390-5194"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Soroush Omidvartehrani","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081503759","display_name":"Arash Nobari","orcid":"https://orcid.org/0000-0003-4634-9227"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Arash Dargahi Nobari","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071837282","display_name":"Davood Rafiei","orcid":"https://orcid.org/0000-0003-2403-0266"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Davood Rafiei","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045831058"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12654399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1229","last_page":"1233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9988999962806702,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9945999979972839,"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":0.764815628528595},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5732295513153076},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4596978425979614},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4551205635070801},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3778950572013855},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3724204897880554},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36213409900665283}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.764815628528595},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5732295513153076},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4596978425979614},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4551205635070801},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3778950572013855},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3724204897880554},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36213409900665283},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701716.3715600","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715600","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715600","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3701716.3715600","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3715600","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3715600","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636879.pdf","grobid_xml":"https://content.openalex.org/works/W4410636879.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1987971958","https://openalex.org/W2116544254","https://openalex.org/W2132525863","https://openalex.org/W2146105230","https://openalex.org/W2150593711","https://openalex.org/W2340222647","https://openalex.org/W2481573984","https://openalex.org/W2496170334","https://openalex.org/W2609779791","https://openalex.org/W2616147950","https://openalex.org/W2889003264","https://openalex.org/W2952363528"],"related_works":["https://openalex.org/W4394360958","https://openalex.org/W2948670949","https://openalex.org/W4288047943","https://openalex.org/W4394193569","https://openalex.org/W1797990060","https://openalex.org/W4232484699","https://openalex.org/W2473636215","https://openalex.org/W4242025311","https://openalex.org/W2990655940","https://openalex.org/W2478535484"],"abstract_inverted_index":{"Describing":[0],"real-world":[1,104],"entities":[2],"varies":[3],"widely":[4],"across":[5],"online":[6],"sources,":[7],"complicating":[8],"the":[9,17,48,58,73,91,96],"task":[10],"of":[11,19,51,60,75,99,119],"web":[12,25,105],"data":[13,84],"integration.":[14],"We":[15],"study":[16],"challenge":[18],"efficiently":[20],"discovering":[21],"syntactic":[22],"transformations":[23,43],"for":[24,78],"tables,":[26],"where":[27],"two":[28,103,117],"tables":[29],"are":[30],"not":[31],"initially":[32],"equi-joinable":[33],"but":[34],"can":[35],"become":[36],"joinable":[37],"after":[38],"some":[39],"transformations.":[40],"Detecting":[41],"these":[42],"is":[44],"challenging":[45],"due":[46],"to":[47,116],"large":[49],"space":[50],"possible":[52],"candidates,":[53],"which":[54],"further":[55],"grows":[56],"with":[57,121],"number":[59,74],"rows.":[61],"To":[62],"overcome":[63],"this,":[64],"we":[65],"introduce":[66],"a":[67],"cluster-based":[68],"table":[69],"sampling":[70],"that":[71,90],"reduces":[72],"required":[76],"rows":[77],"transformation":[79],"generation":[80],"by":[81,114],"capturing":[82],"underlying":[83],"patterns.":[85],"Our":[86],"extensive":[87],"evaluation":[88],"demonstrates":[89],"proposed":[92],"method":[93],"significantly":[94],"improves":[95],"runtime":[97],"performance":[98],"state-of-the-art":[100],"methods":[101],"on":[102,124],"datasets,":[106],"sourced":[107],"from":[108],"webpage":[109],"content":[110],"and":[111],"organizational":[112],"forums,":[113],"one":[115],"orders":[118],"magnitude":[120],"negligible":[122],"impact":[123],"accuracy.":[125]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}