{"id":"https://openalex.org/W3197688135","doi":"https://doi.org/10.14778/3476249.3476293","title":"The smallest extraction problem","display_name":"The smallest extraction problem","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W3197688135","doi":"https://doi.org/10.14778/3476249.3476293","mag":"3197688135"},"language":"en","primary_location":{"id":"doi:10.14778/3476249.3476293","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476249.3476293","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":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11590/404519","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044386001","display_name":"Valerio Cetorelli","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Valerio Cetorelli","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064341104","display_name":"Paolo Atzeni","orcid":"https://orcid.org/0000-0003-1513-4725"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Atzeni","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030700727","display_name":"Valter Crescenzi","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Valter Crescenzi","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017152835","display_name":"Franco Milicchio","orcid":"https://orcid.org/0000-0002-4875-4894"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Franco Milicchio","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044386001"],"corresponding_institution_ids":["https://openalex.org/I119003972"],"apc_list":null,"apc_paid":null,"fwci":0.5688,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73887759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"14","issue":"11","first_page":"2445","last_page":"2458"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9829999804496765,"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/T11478","display_name":"Caching and Content Delivery","score":0.9761999845504761,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8127096891403198},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6951088905334473},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.6387201547622681},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.5913160443305969},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5803617835044861},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5746409296989441},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5611758232116699},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5178109407424927},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.49736884236335754},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4950970709323883},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4790983498096466},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3836575448513031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35756468772888184},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27213090658187866},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25951504707336426},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08004474639892578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8127096891403198},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6951088905334473},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.6387201547622681},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.5913160443305969},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5803617835044861},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5746409296989441},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5611758232116699},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5178109407424927},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.49736884236335754},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4950970709323883},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4790983498096466},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3836575448513031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35756468772888184},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27213090658187866},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25951504707336426},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08004474639892578},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3476249.3476293","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476249.3476293","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:iris.uniroma3.it:11590/404519","is_oa":true,"landing_page_url":"http://hdl.handle.net/11590/404519","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:iris.uniroma3.it:11590/404519","is_oa":true,"landing_page_url":"http://hdl.handle.net/11590/404519","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W279841946","https://openalex.org/W1956354834","https://openalex.org/W1990098488","https://openalex.org/W2002956097","https://openalex.org/W2005646337","https://openalex.org/W2013970953","https://openalex.org/W2022126655","https://openalex.org/W2037504378","https://openalex.org/W2040757233","https://openalex.org/W2052653988","https://openalex.org/W2064466058","https://openalex.org/W2065291336","https://openalex.org/W2089363549","https://openalex.org/W2097033551","https://openalex.org/W2097874932","https://openalex.org/W2104086170","https://openalex.org/W2113004376","https://openalex.org/W2117209866","https://openalex.org/W2122410182","https://openalex.org/W2128341918","https://openalex.org/W2130956967","https://openalex.org/W2134172329","https://openalex.org/W2140327372","https://openalex.org/W2143309843","https://openalex.org/W2148579753","https://openalex.org/W2150721933","https://openalex.org/W2154444297","https://openalex.org/W2154765387","https://openalex.org/W2160189941","https://openalex.org/W2161133055","https://openalex.org/W2161861392","https://openalex.org/W2163072729","https://openalex.org/W2216972693","https://openalex.org/W2296164608","https://openalex.org/W2298437629","https://openalex.org/W2346977452","https://openalex.org/W2421306863","https://openalex.org/W2439475996","https://openalex.org/W2588668235","https://openalex.org/W2781528640","https://openalex.org/W2792180729","https://openalex.org/W2913268761","https://openalex.org/W2913408926","https://openalex.org/W2955858358","https://openalex.org/W2962982640","https://openalex.org/W2968548673","https://openalex.org/W2977125667","https://openalex.org/W2988809464","https://openalex.org/W3001489939","https://openalex.org/W3004954992","https://openalex.org/W3006373977","https://openalex.org/W3021035068","https://openalex.org/W3037151198","https://openalex.org/W3098003395","https://openalex.org/W3098381330","https://openalex.org/W3205169765"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2005087563","https://openalex.org/W2378111931","https://openalex.org/W4243161226","https://openalex.org/W2950647290","https://openalex.org/W2620829895","https://openalex.org/W36911888","https://openalex.org/W4385731361","https://openalex.org/W4280620143"],"abstract_inverted_index":{"We":[0,69],"introduce":[1],"landmark":[2,109],"grammars":[3,10],",":[4],"a":[5,85,90,108,112,117],"new":[6],"family":[7,86],"of":[8,18,41,44,48,57,84,92,114],"context-free":[9],"aimed":[11],"at":[12,28],"describing":[13],"the":[14,38,45,64,72,82,137,144],"HTML":[15,119],"source":[16],"code":[17],"pages":[19,93,115],"published":[20],"by":[21,63],"large":[22],"and":[23,26,94,121],"templated":[24],"websites":[25],"therefore":[27],"effectively":[29],"tackling":[30],"Web":[31,49,126],"data":[32,50,127],"extraction":[33,128],"problems.":[34],"Indeed,":[35],"they":[36],"address":[37],"inherent":[39],"ambiguity":[40],"HTML,":[42],"one":[43],"main":[46],"challenges":[47],"extraction,":[51],"which,":[52],"despite":[53],"over":[54],"twenty":[55],"years":[56],"research,":[58],"has":[59],"been":[60],"largely":[61],"neglected":[62],"approaches":[65],"presented":[66],"in":[67],"literature.":[68],"then":[70],"formalize":[71],"Smallest":[73],"Extraction":[74],"Problem":[75],"(SEP),":[76],"an":[77,102,124],"optimization":[78],"problem":[79],"for":[80],"finding":[81],"grammar":[83,110],"that":[87,136],"best":[88],"describes":[89],"set":[91,113],"contextually":[95],"extract":[96],"their":[97],"data.":[98],"Finally,":[99],"we":[100,122],"present":[101,123],"unsupervised":[103],"learning":[104],"algorithm":[105],"to":[106,142],"induce":[107],"from":[111],"sharing":[116],"common":[118],"template,":[120],"automatic":[125],"system.":[129],"The":[130],"experiments":[131],"on":[132],"consolidated":[133],"benchmarks":[134],"show":[135],"approach":[138],"can":[139],"substantially":[140],"contribute":[141],"improve":[143],"state-of-the-art.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}