{"id":"https://openalex.org/W3096001014","doi":"https://doi.org/10.1145/3428280","title":"Structure interpretation of text formats","display_name":"Structure interpretation of text formats","publication_year":2020,"publication_date":"2020-11-13","ids":{"openalex":"https://openalex.org/W3096001014","doi":"https://doi.org/10.1145/3428280","mag":"3096001014"},"language":"en","primary_location":{"id":"doi:10.1145/3428280","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3428280","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3428280","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/10.1145/3428280","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011543162","display_name":"Sumit Gulwani","orcid":"https://orcid.org/0000-0002-9226-9634"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumit Gulwani","raw_affiliation_strings":["Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051355395","display_name":"Vu Le","orcid":"https://orcid.org/0000-0003-3727-3291"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vu Le","raw_affiliation_strings":["Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000188805","display_name":"Arjun Radhakrishna","orcid":"https://orcid.org/0000-0002-5559-5932"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arjun Radhakrishna","raw_affiliation_strings":["Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060467430","display_name":"Ivan Radi\u010dek","orcid":"https://orcid.org/0000-0002-5106-1837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Radi\u010dek","raw_affiliation_strings":["Microsoft, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Austria","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023425558","display_name":"Mohammad Raza","orcid":"https://orcid.org/0000-0002-2948-7532"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Raza","raw_affiliation_strings":["Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20479526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"4","issue":"OOPSLA","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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":0.9994000196456909,"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/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8720382452011108},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7819029688835144},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6990419626235962},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5866037607192993},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.5566940307617188},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5419299602508545},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.4829072952270508},{"id":"https://openalex.org/keywords/interactivity","display_name":"Interactivity","score":0.45502808690071106},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3276180922985077},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.31348609924316406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.296593576669693},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2767266035079956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8720382452011108},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7819029688835144},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6990419626235962},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5866037607192993},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.5566940307617188},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5419299602508545},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.4829072952270508},{"id":"https://openalex.org/C144430266","wikidata":"https://www.wikidata.org/wiki/Q839721","display_name":"Interactivity","level":2,"score":0.45502808690071106},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3276180922985077},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31348609924316406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.296593576669693},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2767266035079956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3428280","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3428280","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3428280","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:10.1145/3428280","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3428280","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3428280","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":[{"display_name":"Peace, Justice and strong institutions","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3096001014.pdf","grobid_xml":"https://content.openalex.org/works/W3096001014.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2043100293","https://openalex.org/W2054974985","https://openalex.org/W2064766209","https://openalex.org/W2106895292","https://openalex.org/W2113145044","https://openalex.org/W2132667707","https://openalex.org/W2144951274","https://openalex.org/W2150721933","https://openalex.org/W2163072729","https://openalex.org/W2208211896","https://openalex.org/W2536393303","https://openalex.org/W2583874385","https://openalex.org/W2761183833","https://openalex.org/W2896298055","https://openalex.org/W2971324190","https://openalex.org/W4246839229"],"related_works":["https://openalex.org/W2319020389","https://openalex.org/W2001821990","https://openalex.org/W2272707781","https://openalex.org/W2747851897","https://openalex.org/W1975913006","https://openalex.org/W1513662110","https://openalex.org/W2063506784","https://openalex.org/W4240086805","https://openalex.org/W2013411520","https://openalex.org/W4221163897"],"abstract_inverted_index":{"Data":[0],"repositories":[1],"often":[2],"consist":[3],"of":[4,11,20,66,83,112,132,189,194,218,226],"text":[5,220],"files":[6,42,221],"in":[7,24,110,174,236],"a":[8,30,36,44,80,138,148,224],"wide":[9],"variety":[10,193,225],"standard":[12],"formats,":[13,15,102],"ad-hoc":[14,67,85],"as":[16,18,147],"well":[17],"mixtures":[19],"formats":[21],"where":[22,191],"data":[23,55,78,120],"one":[25],"format":[26,88],"is":[27,34,49,92,122,127,229],"embedded":[28],"into":[29,43],"different":[31,162],"format.":[32],"It":[33],"therefore":[35],"significant":[37],"challenge":[38],"to":[39,51,96,114,128,203,231,241],"parse":[40],"these":[41],"structured":[45],"tabular":[46,77],"form,":[47],"which":[48,152],"important":[50],"enable":[52],"any":[53],"downstream":[54],"processing.":[56],"We":[57],"present":[58],"Unravel,":[59],"an":[60],"extensible":[61,95,182],"framework":[62,91],"for":[63,99,208],"structure":[64,155],"interpretation":[65],"formats.":[68],"Unravel":[69,166,228],"can":[70,156,200],"automatically,":[71],"with":[72,179],"no":[73],"user":[74,109],"input,":[75],"extract":[76,232],"from":[79,107,223],"diverse":[81],"range":[82],"standard,":[84],"and":[86,103,134,159],"mixed":[87],"files.":[89],"The":[90],"also":[93,104],"easily":[94],"add":[97],"support":[98],"previously":[100],"unseen":[101],"supports":[105],"interactivity":[106],"the":[108,116,153,171,186,192,233],"terms":[111],"examples":[113],"guide":[115],"system":[117,199],"when":[118],"specialized":[119],"extraction":[121,133],"desired.":[123],"Our":[124],"key":[125],"insight":[126],"allow":[129],"arbitrary":[130],"combination":[131],"parsing":[135],"techniques":[136,173,195],"through":[137,151],"concept":[139],"called":[140],"partial":[141],"structures":[142,145],".":[143],"Partial":[144],"act":[146],"common":[149],"language":[150],"file":[154],"be":[157,201],"shared":[158],"refined":[160],"by":[161,197],"techniques.":[163,243],"This":[164],"makes":[165],"more":[167,238],"powerful":[168],"than":[169],"applying":[170],"individual":[172],"parallel":[175],"or":[176,212],"sequentially.":[177],"Further,":[178],"this":[180],"rule-based":[181],"approach,":[183],"we":[184],"introduce":[185],"novel":[187],"notion":[188],"re-interpretation":[190],"supported":[196],"our":[198,216],"exploited":[202],"improve":[204],"accuracy":[205],"while":[206],"optimizing":[207],"particular":[209],"quality":[210],"measures":[211],"restricted":[213],"environments.":[214],"On":[215],"benchmark":[217],"617":[219],"gathered":[222],"sources,":[227],"able":[230],"intended":[234],"table":[235],"many":[237],"cases":[239],"compared":[240],"state-of-the-art":[242]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
