{"id":"https://openalex.org/W4386128187","doi":"https://doi.org/10.14778/3611479.3611488","title":"REmatch: A Novel Regex Engine for Finding All Matches","display_name":"REmatch: A Novel Regex Engine for Finding All Matches","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W4386128187","doi":"https://doi.org/10.14778/3611479.3611488"},"language":"en","primary_location":{"id":"doi:10.14778/3611479.3611488","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611479.3611488","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/A5083030983","display_name":"Cristian Riveros","orcid":"https://orcid.org/0000-0003-0832-116X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cristian Riveros","raw_affiliation_strings":["PUC Chile &amp; IMFD Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PUC Chile &amp; IMFD Chile","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030494719","display_name":"Nicol\u00e1s Van Sint Jan","orcid":"https://orcid.org/0009-0005-2933-528X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicol\u00e1s Van Sint Jan","raw_affiliation_strings":["PUC Chile &amp; IMFD Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PUC Chile &amp; IMFD Chile","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065838322","display_name":"Domagoj Vrgo\u010d","orcid":"https://orcid.org/0000-0001-5854-2652"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Domagoj Vrgo\u010d","raw_affiliation_strings":["PUC Chile &amp; IMFD Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PUC Chile &amp; IMFD Chile","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.269,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83074815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"16","issue":"11","first_page":"2792","last_page":"2804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9968000054359436,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9965000152587891,"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":0.7837472558021545},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6293017268180847},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6088595986366272},{"id":"https://openalex.org/keywords/enumeration","display_name":"Enumeration","score":0.6075292229652405},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4564644396305084},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3792317807674408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33580631017684937},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19015955924987793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1253381073474884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837472558021545},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6293017268180847},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6088595986366272},{"id":"https://openalex.org/C156340839","wikidata":"https://www.wikidata.org/wiki/Q2704791","display_name":"Enumeration","level":2,"score":0.6075292229652405},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4564644396305084},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3792317807674408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33580631017684937},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19015955924987793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1253381073474884},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3611479.3611488","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611479.3611488","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1548501023","https://openalex.org/W1570445666","https://openalex.org/W1707172707","https://openalex.org/W1833698128","https://openalex.org/W2007130296","https://openalex.org/W2035744833","https://openalex.org/W2072607050","https://openalex.org/W2089302579","https://openalex.org/W2141456009","https://openalex.org/W2170798490","https://openalex.org/W2302109632","https://openalex.org/W2612777267","https://openalex.org/W2895689912","https://openalex.org/W2963265283","https://openalex.org/W2982739078","https://openalex.org/W2990166677","https://openalex.org/W3006809958","https://openalex.org/W3013397275","https://openalex.org/W3037451332","https://openalex.org/W3135245391","https://openalex.org/W3155438827","https://openalex.org/W3184812612","https://openalex.org/W3196855244","https://openalex.org/W4205744525","https://openalex.org/W4282835527","https://openalex.org/W4287642550","https://openalex.org/W4300618478"],"related_works":["https://openalex.org/W108845024","https://openalex.org/W4300125793","https://openalex.org/W2578985712","https://openalex.org/W2406961474","https://openalex.org/W2143566611","https://openalex.org/W2013740965","https://openalex.org/W588267724","https://openalex.org/W4297743441","https://openalex.org/W2952598754","https://openalex.org/W2991618286"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,49],"present":[4],"the":[5,28,56,93,101],"REmatch":[6,11,81],"system":[7],"for":[8,20],"information":[9],"extraction.":[10],"is":[12],"based":[13],"on":[14],"a":[15,33,41,52,61,71,75,103],"recently":[16],"proposed":[17],"enumeration":[18],"algorithm":[19,44,58,73],"evaluating":[21],"regular":[22],"expressions":[23],"with":[24,65],"capture":[25],"variables":[26],"supporting":[27],"all-match":[29],"semantics.":[30],"It":[31],"tells":[32],"story":[34],"of":[35,55,77],"what":[36],"it":[37],"takes":[38],"to":[39,98,110],"make":[40,80],"theoretically":[42],"optimal":[43],"work":[45],"in":[46],"practice.":[47],"As":[48],"show":[50],"here,":[51],"naive":[53],"implementation":[54],"original":[57],"would":[59],"have":[60],"hard":[62],"time":[63,95],"dealing":[64],"realistic":[66],"workloads.":[67],"We":[68],"thus":[69],"develop":[70],"new":[72],"and":[74],"series":[76],"optimizations":[78],"that":[79,105],"as":[82],"fast":[83],"or":[84],"faster":[85],"than":[86],"many":[87],"popular":[88],"RegEx":[89],"engines":[90,108],"while":[91],"at":[92],"same":[94],"being":[96],"able":[97],"return":[99],"all":[100],"outputs:":[102],"task":[104],"most":[106],"other":[107],"tend":[109],"struggle":[111],"with.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
