{"id":"https://openalex.org/W4387667125","doi":"https://doi.org/10.1145/3622863","title":"Data Extraction via Semantic Regular Expression Synthesis","display_name":"Data Extraction via Semantic Regular Expression Synthesis","publication_year":2023,"publication_date":"2023-10-16","ids":{"openalex":"https://openalex.org/W4387667125","doi":"https://doi.org/10.1145/3622863"},"language":"en","primary_location":{"id":"doi:10.1145/3622863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622863","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3622863","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054529146","display_name":"Qiaochu Chen","orcid":"https://orcid.org/0000-0003-4680-5157"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qiaochu Chen","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0003-4680-5157","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103006962","display_name":"Arko Banerjee","orcid":"https://orcid.org/0009-0005-2690-6059"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arko Banerjee","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0009-0005-2690-6059","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027360874","display_name":"\u00c7a\u011fatay Demiralp","orcid":"https://orcid.org/0009-0003-2080-0443"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"\u00c7a\u011fatay Demiralp","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":"https://orcid.org/0009-0003-2080-0443","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015133105","display_name":"Greg Durrett","orcid":"https://orcid.org/0000-0002-7061-7298"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Greg Durrett","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0002-7061-7298","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006424908","display_name":"I\u015f\u0131l Dillig","orcid":"https://orcid.org/0000-0001-8006-1230"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I\u015f\u0131l Dillig","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0001-8006-1230","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054529146"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":3.3116,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93727896,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"7","issue":"OOPSLA2","first_page":"1848","last_page":"1877"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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/T10260","display_name":"Software Engineering Research","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.8533561825752258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6339172124862671},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5962366461753845},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5837447643280029},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.5725859999656677},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.5508161783218384},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.5219242572784424},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4390642046928406},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4365310072898865},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35022950172424316},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1637977957725525},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11563950777053833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8533561825752258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6339172124862671},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5962366461753845},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5837447643280029},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.5725859999656677},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.5508161783218384},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.5219242572784424},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4390642046928406},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4365310072898865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35022950172424316},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1637977957725525},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11563950777053833},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3622863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622863","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3622863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622863","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4104542924","display_name":"SHF: Medium: Collaborative Research: Computer-Aided Programming for Data Science","funder_award_id":"1762299","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5072487302","display_name":null,"funder_award_id":"1918889,1762299","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6208393420","display_name":null,"funder_award_id":"1918889","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387667125.pdf","grobid_xml":"https://content.openalex.org/works/W4387667125.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1858945639","https://openalex.org/W1878188374","https://openalex.org/W1989445634","https://openalex.org/W1998368317","https://openalex.org/W2013596093","https://openalex.org/W2017603160","https://openalex.org/W2060610732","https://openalex.org/W2093535699","https://openalex.org/W2144951274","https://openalex.org/W2153225416","https://openalex.org/W2251623545","https://openalex.org/W2263738566","https://openalex.org/W2531982678","https://openalex.org/W2550471858","https://openalex.org/W2595326376","https://openalex.org/W2604259521","https://openalex.org/W2913668833","https://openalex.org/W2963143606","https://openalex.org/W2963899988","https://openalex.org/W2964118342","https://openalex.org/W2964240296","https://openalex.org/W2988809464","https://openalex.org/W3033316151","https://openalex.org/W3033889389","https://openalex.org/W3081176230","https://openalex.org/W3092838946","https://openalex.org/W3099461227","https://openalex.org/W3171035942","https://openalex.org/W3205887319","https://openalex.org/W3205927779","https://openalex.org/W3206370442","https://openalex.org/W4205326975","https://openalex.org/W4212774754","https://openalex.org/W4225533190","https://openalex.org/W4226226396","https://openalex.org/W4237109062","https://openalex.org/W4237412827","https://openalex.org/W4281943563","https://openalex.org/W4284676027","https://openalex.org/W4319866878","https://openalex.org/W6894151968"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W1986106996","https://openalex.org/W4285012873","https://openalex.org/W2122517733"],"abstract_inverted_index":{"Many":[0],"data":[1,43,140,157],"extraction":[2,44,141,158],"tasks":[3,32,45,142,159],"of":[4,20,64,93,105,122],"practical":[5],"relevance":[6],"require":[7,34],"not":[8],"only":[9,35],"syntactic":[10,36,50,70],"pattern":[11,37],"matching":[12],"but":[13],"also":[14,78],"semantic":[15,52,60,72,87,151],"reasoning":[16,73],"about":[17,74],"the":[18,21],"content":[19],"underlying":[22],"text.":[23],"While":[24],"regular":[25,65,162],"expressions":[26,66,163],"are":[27],"very":[28],"well":[29],"suited":[30],"for":[31,42,113],"that":[33,46,67,84,150,165],"matching,":[38],"they":[39],"fall":[40],"short":[41],"involve":[47],"both":[48],"a":[49,62,80,90,103,119,130],"and":[51,71,95,109,115,135,164,177],"component.":[53],"To":[54],"address":[55],"this":[56],"issue,":[57],"we":[58],"introduce":[59],"regexes,":[61],"generalization":[63,117],"facilitates":[68],"combined":[69],"textual":[75,145],"data.":[76],"We":[77,124],"propose":[79],"novel":[81],"learning":[82,100,167],"algorithm":[83,101,168],"can":[85,153],"synthesize":[86],"regexes":[88,152],"from":[89,118],"small":[91,120],"number":[92,121],"positive":[94],"negative":[96],"examples.":[97,123],"Our":[98,147],"proposed":[99],"uses":[102],"combination":[104],"neural":[106,175],"sketch":[107],"generation":[108],"compositional":[110],"type-directed":[111],"synthesis":[112,179],"fast":[114],"effective":[116],"have":[125],"implemented":[126],"these":[127],"ideas":[128],"in":[129],"new":[131],"tool":[132],"called":[133],"Smore":[134],"evaluated":[136],"it":[137],"on":[138],"representative":[139],"involving":[143],"several":[144],"datasets.":[146],"evaluation":[148],"shows":[149],"better":[154],"support":[155],"complex":[156],"than":[160],"standard":[161],"our":[166],"significantly":[169],"outperforms":[170],"existing":[171],"tools,":[172],"including":[173],"state-of-the-art":[174],"networks":[176],"program":[178],"tools.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6}],"updated_date":"2026-05-24T08:33:08.758527","created_date":"2025-10-10T00:00:00"}