{"id":"https://openalex.org/W2895689912","doi":"https://doi.org/10.1145/3294052.3319684","title":"Split-Correctness in Information Extraction","display_name":"Split-Correctness in Information Extraction","publication_year":2019,"publication_date":"2019-06-17","ids":{"openalex":"https://openalex.org/W2895689912","doi":"https://doi.org/10.1145/3294052.3319684","mag":"2895689912"},"language":"en","primary_location":{"id":"doi:10.1145/3294052.3319684","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3294052.3319684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","raw_type":"proceedings-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/A5082548231","display_name":"Johannes Doleschal","orcid":null},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Johannes Doleschal","raw_affiliation_strings":["University of Bayreuth &amp; Hasselt University, Bayreuth, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bayreuth &amp; Hasselt University, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006706357","display_name":"Benny Kimelfeld","orcid":"https://orcid.org/0000-0002-7156-1572"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Benny Kimelfeld","raw_affiliation_strings":["Technion - Israel Institute of Technology, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Technion - Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016412428","display_name":"Wim Martens","orcid":"https://orcid.org/0000-0001-9480-3522"},"institutions":[{"id":"https://openalex.org/I54009628","display_name":"University of Bayreuth","ror":"https://ror.org/0234wmv40","country_code":"DE","type":"education","lineage":["https://openalex.org/I54009628"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wim Martens","raw_affiliation_strings":["University of Bayreuth, Bayreuth, Germany"],"affiliations":[{"raw_affiliation_string":"University of Bayreuth, Bayreuth, Germany","institution_ids":["https://openalex.org/I54009628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041879684","display_name":"Yoav Nahshon","orcid":"https://orcid.org/0000-0003-4774-8764"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yoav Nahshon","raw_affiliation_strings":["Technion - Israel Institute of Technology, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"Technion - Israel Institute of Technology, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022264843","display_name":"Frank Neven","orcid":"https://orcid.org/0000-0002-7143-1903"},"institutions":[{"id":"https://openalex.org/I878454856","display_name":"Hasselt University","ror":"https://ror.org/04nbhqj75","country_code":"BE","type":"education","lineage":["https://openalex.org/I878454856"]},{"id":"https://openalex.org/I4210127597","display_name":"Transnational University Limburg","ror":"https://ror.org/02xyaf767","country_code":"BE","type":"education","lineage":["https://openalex.org/I4210127597"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Frank Neven","raw_affiliation_strings":["Hasselt University &amp; Transnational University of Limburg, Hasselt, Belgium"],"affiliations":[{"raw_affiliation_string":"Hasselt University &amp; Transnational University of Limburg, Hasselt, Belgium","institution_ids":["https://openalex.org/I4210127597","https://openalex.org/I878454856"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082548231"],"corresponding_institution_ids":["https://openalex.org/I54009628"],"apc_list":null,"apc_paid":null,"fwci":1.8786,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89143645,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"149","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.9683899879455566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.847516655921936},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.6275629997253418},{"id":"https://openalex.org/keywords/formalism","display_name":"Formalism (music)","score":0.5570265650749207},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4976537525653839},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.44278261065483093},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42886820435523987},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3680174648761749},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33604228496551514}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.9683899879455566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847516655921936},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6275629997253418},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.5570265650749207},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4976537525653839},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.44278261065483093},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42886820435523987},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3680174648761749},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33604228496551514},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3294052.3319684","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3294052.3319684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","raw_type":"proceedings-article"},{"id":"pmh:oai::52815","is_oa":false,"landing_page_url":"https://eref.uni-bayreuth.de/52815/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"pmh:oai:documentserver.uhasselt.be:1942/29007","is_oa":false,"landing_page_url":"http://hdl.handle.net/1942/29007","pdf_url":null,"source":{"id":"https://openalex.org/S4306401926","display_name":"Document Server@UHasselt (UHasselt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I878454856","host_organization_name":"Hasselt University","host_organization_lineage":["https://openalex.org/I878454856"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Meeting","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1055682243","display_name":null,"funder_award_id":"4938/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3881880258","display_name":null,"funder_award_id":"1295/15","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G5106512922","display_name":null,"funder_award_id":"Deutsche Forschungsgemeinschaft (DFG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6024419964","display_name":null,"funder_award_id":"Deutsche Forschungsgemeinschaft (DFG)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6052429835","display_name":null,"funder_award_id":"(DFG)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6237554526","display_name":null,"funder_award_id":"MA 4938/4-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7315415636","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G75832214","display_name":null,"funder_award_id":"1295/15","funder_id":"https://openalex.org/F4320320950","funder_display_name":"United States-Israel Binational Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320320950","display_name":"United States-Israel Binational Science Foundation","ror":"https://ror.org/00j8z2m73"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"},{"id":"https://openalex.org/F4320325866","display_name":"Universiteit Hasselt","ror":"https://ror.org/04nbhqj75"},{"id":"https://openalex.org/F4320335227","display_name":"Bijzonder Onderzoeksfonds UGent","ror":"https://ror.org/00cv9y106"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1423339008","https://openalex.org/W1493270114","https://openalex.org/W1495981708","https://openalex.org/W1828401780","https://openalex.org/W1934084512","https://openalex.org/W1983298175","https://openalex.org/W1996430422","https://openalex.org/W2039529128","https://openalex.org/W2039654728","https://openalex.org/W2059200976","https://openalex.org/W2098720114","https://openalex.org/W2107005506","https://openalex.org/W2114524997","https://openalex.org/W2129657639","https://openalex.org/W2134781086","https://openalex.org/W2141456009","https://openalex.org/W2144416276","https://openalex.org/W2164455818","https://openalex.org/W2251135946","https://openalex.org/W2296283641","https://openalex.org/W2319151433","https://openalex.org/W2363785281","https://openalex.org/W2466758040","https://openalex.org/W2525579820","https://openalex.org/W2542459869","https://openalex.org/W2565515778","https://openalex.org/W2594789930","https://openalex.org/W2604165918","https://openalex.org/W2606231744","https://openalex.org/W2616567161","https://openalex.org/W2724745846","https://openalex.org/W2724969572","https://openalex.org/W2750884547","https://openalex.org/W2785321994","https://openalex.org/W2962679309","https://openalex.org/W2963265283","https://openalex.org/W2963625095","https://openalex.org/W3195236188","https://openalex.org/W4206399782","https://openalex.org/W4299146188","https://openalex.org/W4313371817","https://openalex.org/W6685810106","https://openalex.org/W6740402979"],"related_works":["https://openalex.org/W3008339103","https://openalex.org/W2404647514","https://openalex.org/W1667647204","https://openalex.org/W4247536566","https://openalex.org/W3119814709","https://openalex.org/W4321442002","https://openalex.org/W2018477250","https://openalex.org/W1508895727","https://openalex.org/W2015265939","https://openalex.org/W2061417947"],"abstract_inverted_index":{"Programs":[0],"for":[1,60,110,136],"extracting":[2],"structured":[3],"information":[4,8,79,92],"from":[5,17],"text,":[6],"namely":[7],"extractors,":[9,39],"often":[10],"operate":[11],"separately":[12],"on":[13,58,73],"document":[14,116],"segments":[15,59],"obtained":[16],"a":[18,106],"generic":[19],"splitting":[20],"operation":[21],"such":[22],"as":[23,44],"sentences,":[24],"paragraphs,":[25],"k-grams,":[26],"HTTP":[27],"requests,":[28],"and":[29,87],"so":[30],"on.":[31],"An":[32],"automated":[33],"detection":[34],"of":[35,38,64,78,91,100,115,124,134,141],"this":[36],"behavior":[37],"which":[40],"we":[41],"refer":[42],"to":[43,51,84],"split-correctness,":[45,135],"would":[46],"allow":[47],"text":[48],"analysis":[49,120],"systems":[50],"devise":[52],"query":[53],"plans":[54],"with":[55,144],"parallel":[56],"evaluation":[57,72],"accelerating":[61],"the":[62,70,113,122,139],"processing":[63],"large":[65],"documents.":[66],"Other":[67],"applications":[68],"include":[69],"incremental":[71],"dynamic":[74],"content,":[75],"where":[76,89],"re-evaluation":[77],"extractors":[80,93,143],"can":[81],"be":[82],"restricted":[83],"revised":[85],"segments,":[86],"debugging,":[88],"developers":[90],"are":[94],"informed":[95],"about":[96],"potential":[97],"boundary":[98],"crossing":[99],"different":[101,132],"semantic":[102],"components.":[103],"We":[104,129],"propose":[105],"new":[107],"formal":[108],"framework":[109],"split-correctness":[111,125],"within":[112],"formalism":[114],"spanners.":[117,128],"Our":[118],"preliminary":[119],"studies":[121],"complexity":[123],"over":[126],"regular":[127],"also":[130],"discuss":[131],"variants":[133],"instance,":[137],"in":[138],"presence":[140],"black-box":[142],"\"split":[145],"constraints\".":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
