{"id":"https://openalex.org/W3198906529","doi":"https://doi.org/10.15495/epub_ubt_00005737","title":"Optimization and Parallelization of RegEx Based Information Extraction","display_name":"Optimization and Parallelization of RegEx Based Information Extraction","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3198906529","doi":"https://doi.org/10.15495/epub_ubt_00005737","mag":"3198906529"},"language":"en","primary_location":{"id":"pmh:oai:epub.uni-bayreuth.de:5737","is_oa":true,"landing_page_url":null,"pdf_url":"https://epub.uni-bayreuth.de/5737/3/DissertationJohannesDoleschal.pdf","source":{"id":"https://openalex.org/S4306400362","display_name":"EPub Bayreuth (University of Bayreuth)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I54009628","host_organization_name":"University of Bayreuth","host_organization_lineage":["https://openalex.org/I54009628"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://epub.uni-bayreuth.de/5737/3/DissertationJohannesDoleschal.pdf","any_repository_has_fulltext":true},"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":"Doleschal, Johannes","raw_affiliation_strings":["University of Bayreuth"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bayreuth","institution_ids":["https://openalex.org/I54009628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5082548231"],"corresponding_institution_ids":["https://openalex.org/I54009628"],"apc_list":null,"apc_paid":null,"fwci":0.8315,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79219519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.8500000238418579,"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":0.8500000238418579,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.7386999726295471,"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":0.6881134510040283},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6136614680290222},{"id":"https://openalex.org/keywords/automatic-parallelization","display_name":"Automatic parallelization","score":0.49813294410705566},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4884423315525055},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.42129209637641907},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2899749279022217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2616967260837555},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.062311530113220215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6881134510040283},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6136614680290222},{"id":"https://openalex.org/C164833996","wikidata":"https://www.wikidata.org/wiki/Q2323839","display_name":"Automatic parallelization","level":3,"score":0.49813294410705566},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4884423315525055},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.42129209637641907},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2899749279022217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2616967260837555},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.062311530113220215},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:epub.uni-bayreuth.de:5737","is_oa":true,"landing_page_url":null,"pdf_url":"https://epub.uni-bayreuth.de/5737/3/DissertationJohannesDoleschal.pdf","source":{"id":"https://openalex.org/S4306400362","display_name":"EPub Bayreuth (University of Bayreuth)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I54009628","host_organization_name":"University of Bayreuth","host_organization_lineage":["https://openalex.org/I54009628"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"pmh:oai:aleph.bib-bvb.de:BVB01-032888736","is_oa":false,"landing_page_url":"https://epub.uni-bayreuth.de/5737/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Hochschulschrift"},{"id":"pmh:oai:documentserver.uhasselt.be:1942/34769","is_oa":false,"landing_page_url":"http://hdl.handle.net/1942/34769","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":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"doi:10.15495/epub_ubt_00005737","is_oa":true,"landing_page_url":"https://doi.org/10.15495/epub_ubt_00005737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400362","display_name":"EPub Bayreuth (University of Bayreuth)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I54009628","host_organization_name":"University of Bayreuth","host_organization_lineage":["https://openalex.org/I54009628"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:epub.uni-bayreuth.de:5737","is_oa":true,"landing_page_url":null,"pdf_url":"https://epub.uni-bayreuth.de/5737/3/DissertationJohannesDoleschal.pdf","source":{"id":"https://openalex.org/S4306400362","display_name":"EPub Bayreuth (University of Bayreuth)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I54009628","host_organization_name":"University of Bayreuth","host_organization_lineage":["https://openalex.org/I54009628"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3198906529.pdf","grobid_xml":"https://content.openalex.org/works/W3198906529.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2476420530","https://openalex.org/W2483095339","https://openalex.org/W2336009576","https://openalex.org/W2171763141","https://openalex.org/W111605429","https://openalex.org/W3195620503","https://openalex.org/W3084243021","https://openalex.org/W334115181","https://openalex.org/W3173180673","https://openalex.org/W2563076175","https://openalex.org/W3150723689","https://openalex.org/W1991674304","https://openalex.org/W2287285612","https://openalex.org/W1554023280","https://openalex.org/W2158244147","https://openalex.org/W2059147475","https://openalex.org/W2098644672","https://openalex.org/W3099578377","https://openalex.org/W2924329194","https://openalex.org/W2770883301"],"abstract_inverted_index":{"The":[0,55],"framework":[1,219],"of":[2,8,58,68,71,79,89,93,103,143,146,172,186,199,208,225,233,243,250,266,290,300,308,371,385,392,402,408,413,432,448,468],"document":[3,19,41,94,104,122,226,267,339,450,461],"spanners":[4,42,61,268,462],"abstracts":[5],"the":[6,26,39,44,52,59,66,77,87,170,178,223,231,248,264,288,306,314,318,324,328,345,375,378,390,400,414,429,465],"task":[7],"information":[9,112,116,187,200,275],"extraction":[10],"from":[11,113,125],"text":[12,156,434],"as":[13,131,152,277,334,374,389,418,440],"a":[14,23,126,216,301,309,348,406,479],"function":[15],"that":[16,75,269,477],"maps":[17,337],"every":[18,338],"(a":[20],"string)":[21],"into":[22,340],"relation":[24,302,343],"over":[25,235,344,460],"document\u2019s":[27],"spans":[28],"(intervals":[29],"identified":[30],"by":[31,65,293,435],"their":[32,396],"start":[33],"and":[34,101,137,195,214,280,296,312,360,382,395,443,463,470],"end":[35],"indices).":[36],"For":[37,405],"instance,":[38,246],"regular":[40,45,60,236,449],"are":[43,202,303,420],"expressions":[46],"with":[47,163,253,273,305,507],"capture":[48],"variables,":[49],"closed":[50],"under":[51,377],"relational":[53,320,380],"algebra.":[54],"expressive":[56],"power":[57],"is":[62,499],"precisely":[63],"captured":[64],"class":[67],"vset-automata\u2014an":[69],"extension":[70],"finite":[72],"state":[73],"automata,":[74],"mark":[76],"endpoints":[78],"selected":[80],"spans.":[81,346],"In":[82,492],"this":[83,144,284,453],"thesis,":[84],"we":[85,149,261,286,351,427,455,475],"embark":[86,262],"investigation":[88,265],"multiple":[90],"different":[91,209,241],"aspects":[92,370,384],"spanners.":[95,105,227,237,451],"Namely,":[96],"parallel":[97,164],"evaluation,":[98],"weight":[99,259],"annotation,":[100,260],"aggregation":[102],"Parallel":[106],"Evaluation:":[107],"Programs":[108],"for":[109,168,220,245,422],"extracting":[110],"structured":[111],"text,":[114],"namely":[115],"extractors,":[117,147],"often":[118],"operate":[119],"separately":[120],"on":[121,166,181,263,446],"segments":[123,167],"obtained":[124],"generic":[127],"splitting":[128],"operation":[129],"such":[130,276,373,388,417,439],"sentences,":[132],"paragraphs,":[133],"k-grams,":[134],"HTTP":[135],"requests,":[136],"so":[138],"on.":[139],"An":[140],"automated":[141],"detection":[142],"behavior":[145],"which":[148],"refer":[150],"to":[151,159,192,333,357,365],"split-correctness,":[153,244],"would":[154],"allow":[155],"analysis":[157,229],"systems":[158],"devise":[160],"query":[161],"plans":[162],"evaluation":[165,180],"accelerating":[169],"processing":[171],"large":[173],"documents.":[174],"Other":[175],"applications":[176],"include":[177],"incremental":[179],"dynamic":[182],"content,":[183],"where":[184,197,298,313],"re-evaluation":[185],"extractors":[188,201,252],"can":[189,270,486,503],"be":[190,487,505],"restricted":[191,480],"revised":[193],"segments,":[194],"debugging,":[196],"developers":[198],"informed":[203],"about":[204],"potential":[205],"boundary":[206],"crossing":[207],"semantic":[210],"components.":[211],"We":[212,238,367],"propose":[213],"study":[215],"new":[217],"formal":[218],"split-correctness":[221,234],"within":[222],"formalism":[224],"Our":[228],"studies":[230],"complexity":[232,431,467],"also":[239],"discuss":[240],"variants":[242],"in":[247,399,478,489],"presence":[249],"black-box":[251],"split":[254],"constraints.":[255],"Weight":[256],"Annotation:":[257],"Concerning":[258],"annotate":[271],"extractions":[272],"auxiliary":[274],"confidence,":[278],"support,":[279],"confidentiality":[281],"measures.":[282],"To":[283,452],"end,":[285,454],"adopt":[287],"abstraction":[289],"provenance":[291],"semirings":[292],"Green,":[294],"Karvounarakis,":[295],"Tannen,":[297],"tuples":[299],"annotated":[304,342,393],"elements":[307,364],"commutative":[310],"semiring,":[311,416],"annotation":[315],"propagates":[316],"through":[317],"positive":[319,379],"Algebra":[321],"operators":[322],"via":[323],"semiring":[325,363],"operators.":[326],"Hence,":[327],"proposed":[329],"spanner":[330],"extension,":[331],"referred":[332],"an":[335,341],"annotator,":[336],"As":[347],"specific":[349],"instantiation,":[350],"explore":[352],"weighted":[353,358],"vset-automata":[354],"that,":[355],"similarly":[356],"automata":[359],"transducers,":[361],"attach":[362],"transitions.":[366],"investigate":[368,428],"key":[369,383],"expressiveness,":[372],"closure":[376],"Algebra,":[381],"computational":[386,430,466],"complexity,":[387],"enumeration":[391,398],"answers":[394],"ranked":[397],"case":[401],"ordered":[403],"semirings.":[404],"number":[407],"these":[409],"problems,":[410],"fundamental":[411],"properties":[412],"underlying":[415],"positivity,":[419],"crucial":[421],"establishing":[423],"tractability.":[424],"Aggregation:":[425],"Lastly":[426],"querying":[433],"aggregate":[436,458,484],"functions":[437,459,485],"\u2014":[438,445],"sum,":[441],"average,":[442],"quantile":[444],"top":[447],"formally":[456],"define":[457],"analyze":[464],"exact":[469,497],"approximate":[471],"computation.":[472],"More":[473],"precisely,":[474],"show":[476],"case,":[481],"all":[482],"studied":[483],"computed":[488],"polynomial":[490],"time.":[491],"general,":[493],"however,":[494],"even":[495],"though":[496],"computation":[498],"intractable,":[500],"some":[501],"aggregates":[502],"still":[504],"approximated":[506],"fully":[508],"polynomial-time":[509],"randomized":[510],"approximation":[511],"schemes":[512],"(FPRAS).":[513]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}