{"id":"https://openalex.org/W3100432815","doi":"https://doi.org/10.1162/tacl_a_00339","title":"Sketch-Driven Regular Expression Generation from Natural Language and Examples","display_name":"Sketch-Driven Regular Expression Generation from Natural Language and Examples","publication_year":2020,"publication_date":"2020-11-12","ids":{"openalex":"https://openalex.org/W3100432815","doi":"https://doi.org/10.1162/tacl_a_00339","mag":"3100432815"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00339","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00339","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00339/1923648/tacl_a_00339.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00339/1923648/tacl_a_00339.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073604585","display_name":"Xi Ye","orcid":null},"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":"Xi Ye","raw_affiliation_strings":["Department of Computer Science, The University of Texas at Austin","Department of Computer Science, The University of Texas at Austin, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080099797","display_name":"Qiaochu Chen","orcid":"https://orcid.org/0000-0002-7384-7574"},"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":["Department of Computer Science, The University of Texas at Austin","Department of Computer Science, The University of Texas at Austin, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352782","display_name":"Xinyu Wang","orcid":"https://orcid.org/0000-0002-1836-0202"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinyu Wang","raw_affiliation_strings":["Computer Science and Engineering Department, University of Michigan, Ann Arbor","Computer Science and Engineering Department, University of Michigan, Ann Arbor, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, University of Michigan, Ann Arbor","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Computer Science and Engineering Department, University of Michigan, Ann Arbor, United States","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","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":true,"raw_author_name":"Isil Dillig","raw_affiliation_strings":["Department of Computer Science, The University of Texas at Austin","Department of Computer Science, The University of Texas at Austin, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","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":true,"raw_author_name":"Greg Durrett","raw_affiliation_strings":["Department of Computer Science, The University of Texas at Austin","Department of Computer Science, The University of Texas at Austin, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006424908","https://openalex.org/A5015133105","https://openalex.org/A5073604585","https://openalex.org/A5080099797","https://openalex.org/A5100352782"],"corresponding_institution_ids":["https://openalex.org/I27837315","https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":2.4122,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91138145,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"8","issue":null,"first_page":"679","last_page":"694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987999796867371,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8936165571212769},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.7712621688842773},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6815980076789856},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6397202014923096},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5479791164398193},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5385026335716248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5333473682403564},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.48824313282966614},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4428880214691162},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35042789578437805},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17791712284088135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8936165571212769},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.7712621688842773},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6815980076789856},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6397202014923096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5479791164398193},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5385026335716248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333473682403564},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.48824313282966614},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4428880214691162},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35042789578437805},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17791712284088135}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00339","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00339","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00339/1923648/tacl_a_00339.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1da3065e722e424292a764be341a1a5e","is_oa":false,"landing_page_url":"https://doaj.org/article/1da3065e722e424292a764be341a1a5e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 8 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00339","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00339","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00339/1923648/tacl_a_00339.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1526922602","https://openalex.org/W1985602891","https://openalex.org/W2070473038","https://openalex.org/W2132525863","https://openalex.org/W2142898321","https://openalex.org/W2158396456","https://openalex.org/W2175619924","https://openalex.org/W2224454470","https://openalex.org/W2250623140","https://openalex.org/W2251673953","https://openalex.org/W2252136820","https://openalex.org/W2276356546","https://openalex.org/W2304240348","https://openalex.org/W2489487449","https://openalex.org/W2509361447","https://openalex.org/W2531982678","https://openalex.org/W2536870052","https://openalex.org/W2550100435","https://openalex.org/W2605887895","https://openalex.org/W2610403318","https://openalex.org/W2611818442","https://openalex.org/W2612649659","https://openalex.org/W2762513422","https://openalex.org/W2785439365","https://openalex.org/W2786248241","https://openalex.org/W2788109215","https://openalex.org/W2796979813","https://openalex.org/W2887312980","https://openalex.org/W2890260889","https://openalex.org/W2896392119","https://openalex.org/W2930957955","https://openalex.org/W2938905894","https://openalex.org/W2949335953","https://openalex.org/W2950006889","https://openalex.org/W2950621612","https://openalex.org/W2955270045","https://openalex.org/W2962728167","https://openalex.org/W2964121744","https://openalex.org/W2964240296","https://openalex.org/W2970971581","https://openalex.org/W2971034829","https://openalex.org/W2972564045","https://openalex.org/W2994962993","https://openalex.org/W3035299118","https://openalex.org/W4234229576","https://openalex.org/W4242607726","https://openalex.org/W4300336259","https://openalex.org/W4310895557"],"related_works":["https://openalex.org/W3136824659","https://openalex.org/W382594479","https://openalex.org/W2152921782","https://openalex.org/W2293063786","https://openalex.org/W2470045054","https://openalex.org/W2575772232","https://openalex.org/W2911292476","https://openalex.org/W2140902089","https://openalex.org/W2030298461","https://openalex.org/W3014316498"],"abstract_inverted_index":{"Recent":[0],"systems":[1,186],"for":[2,52],"converting":[3],"natural":[4,60,77],"language":[5,61,78],"descriptions":[6],"into":[7,80],"regular":[8],"expressions":[9],"(regexes)":[10],"have":[11],"achieved":[12],"some":[13],"success,":[14],"but":[15],"typically":[16],"deal":[17],"with":[18,35,115],"short,":[19],"formulaic":[20],"text":[21],"and":[22,38,63,108,151,160,176],"can":[23,123,139],"only":[24],"produce":[25],"simple":[26],"regexes.":[27],"Real-world":[28],"regexes":[29],"are":[30,65],"complex,":[31],"hard":[32],"to":[33,42,91],"describe":[34],"brief":[36],"sentences,":[37],"sometimes":[39],"require":[40],"examples":[41,64],"fully":[43],"convey":[44],"the":[45,76,101,106,116,134,173,180],"user\u2019s":[46],"intent.":[47],"We":[48,144],"present":[49],"a":[50,68,96,110,161],"framework":[51],"regex":[53,88,102,111],"synthesis":[54],"in":[55],"this":[56],"setting":[57],"where":[58],"both":[59],"(NL)":[62],"available.":[66],"First,":[67],"semantic":[69,121],"parser":[70,122],"(either":[71],"grammar-based":[72],"or":[73,137],"neural)":[74],"maps":[75],"description":[79],"an":[81,86],"intermediate":[82],"sketch,":[83],"which":[84,183],"is":[85,113],"incomplete":[87],"containing":[89],"holes":[90],"denote":[92],"missing":[93],"components.":[94],"Then":[95],"program":[97],"synthesizer":[98],"searches":[99],"over":[100],"space":[103],"defined":[104],"by":[105],"sketch":[107],"finds":[109],"that":[112],"consistent":[114],"given":[117],"string":[118],"examples.":[119],"Our":[120,167],"be":[124],"trained":[125],"purely":[126],"from":[127,164],"weak":[128],"supervision":[129],"based":[130],"on":[131,146,172],"correctness":[132],"of":[133,179],"synthesized":[135],"regex,":[136],"it":[138],"leverage":[140],"heuristically":[141],"derived":[142],"sketches.":[143],"evaluate":[145],"two":[147],"prior":[148,174],"datasets":[149,175],"(Kushman":[150],"Barzilay":[152],"2013":[153],";":[154],"Locascio":[155],"et":[156],"al.":[157],"2016":[158],")":[159],"real-world":[162,181],"dataset":[163],"Stack":[165],"Overflow.":[166],"system":[168],"achieves":[169],"state-of-the-art":[170],"performance":[171],"solves":[177],"57%":[178],"dataset,":[182],"existing":[184],"neural":[185],"completely":[187],"fail":[188],"on.":[189],"1":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}