{"id":"https://openalex.org/W2061503494","doi":"https://doi.org/10.1145/1806596.1806622","title":"A context-free markup language for semi-structured text","display_name":"A context-free markup language for semi-structured text","publication_year":2010,"publication_date":"2010-06-05","ids":{"openalex":"https://openalex.org/W2061503494","doi":"https://doi.org/10.1145/1806596.1806622","mag":"2061503494"},"language":"en","primary_location":{"id":"doi:10.1145/1806596.1806622","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1806596.1806622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Conference on Programming Language Design and Implementation","raw_type":"proceedings-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/A5009455598","display_name":"Qian Xi","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qian Xi","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA","Princeton University , Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton University , Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049454219","display_name":"David Walker","orcid":"https://orcid.org/0000-0003-3681-149X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Walker","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA","Princeton University , Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton University , Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009455598"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":2.0811,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90892465,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"221","last_page":"232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9991000294685364,"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":0.9015812873840332},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.670479953289032},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6698819398880005},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6299833655357361},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.5978958606719971},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45664167404174805},{"id":"https://openalex.org/keywords/sgml","display_name":"SGML","score":0.4455066919326782},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4177817404270172},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.41701456904411316},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.4138231873512268},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3596937656402588},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.3215232491493225},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2644926905632019}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9015812873840332},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.670479953289032},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6698819398880005},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6299833655357361},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.5978958606719971},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45664167404174805},{"id":"https://openalex.org/C62701983","wikidata":"https://www.wikidata.org/wiki/Q207819","display_name":"SGML","level":4,"score":0.4455066919326782},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4177817404270172},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.41701456904411316},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.4138231873512268},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3596937656402588},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.3215232491493225},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2644926905632019},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1806596.1806622","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1806596.1806622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Conference on Programming Language Design and Implementation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W5832829","https://openalex.org/W140384553","https://openalex.org/W1503682011","https://openalex.org/W1541410883","https://openalex.org/W1553019137","https://openalex.org/W1575798196","https://openalex.org/W1593617641","https://openalex.org/W1652311832","https://openalex.org/W1679509962","https://openalex.org/W1969005071","https://openalex.org/W1982280055","https://openalex.org/W1990751139","https://openalex.org/W1991221934","https://openalex.org/W2031469331","https://openalex.org/W2034797903","https://openalex.org/W2095745830","https://openalex.org/W2096496923","https://openalex.org/W2096679454","https://openalex.org/W2104086170","https://openalex.org/W2106895292","https://openalex.org/W2109486375","https://openalex.org/W2132843347","https://openalex.org/W2134164043","https://openalex.org/W2141950720","https://openalex.org/W2149827273","https://openalex.org/W2150721933","https://openalex.org/W2162340487","https://openalex.org/W2168679495","https://openalex.org/W2610715702","https://openalex.org/W4229774919","https://openalex.org/W4232537713","https://openalex.org/W4241226388","https://openalex.org/W4246839229","https://openalex.org/W4248513939"],"related_works":["https://openalex.org/W2044641582","https://openalex.org/W2186877208","https://openalex.org/W2084734328","https://openalex.org/W4232022739","https://openalex.org/W4244715874","https://openalex.org/W2076638146","https://openalex.org/W2060814800","https://openalex.org/W1971521465","https://openalex.org/W1519732405","https://openalex.org/W4230652012"],"abstract_inverted_index":{"An":[0],"ad":[1,44,53],"hoc":[2,45,54],"data":[3,9,14,40,55,105,125,164,173],"format":[4,10,165],"is":[5],"any":[6],"nonstandard,":[7],"semi-structured":[8],"for":[11,43,141],"which":[12,70,134,155],"robust":[13],"processing":[15,41,174],"tools":[16,42],"are":[17],"not":[18],"easily":[19],"available.":[20],"In":[21,146],"this":[22],"paper,":[23],"we":[24],"present":[25],"ANNE,":[26],"a":[27,51,65,97,109,139,152,169],"new":[28,52],"kind":[29],"of":[30,67,99,162,171],"markup":[31],"language":[32],"designed":[33],"to":[34,63,72,107,122],"help":[35],"users":[36],"generate":[37],"documentation":[38,161],"and":[39,90,102,126],"text":[46],"data.":[47],"More":[48],"specifically,":[49],"given":[50],"source,":[56],"an":[57,130],"ANNE":[58,94,149],"programmer":[59],"edits":[60],"the":[61,103,113,124,148,163],"document":[62],"add":[64],"number":[66],"simple":[68],"annotations,":[69],"serve":[71],"specify":[73,81],"its":[74],"syntactic":[75],"structure.":[76],"Annotations":[77],"include":[78],"elements":[79],"that":[80],"constants,":[82],"optional":[83],"data,":[84,89],"alternatives,":[85],"enumerations,":[86],"sequences,":[87],"tabular":[88],"recursive":[91],"patterns.":[92],"The":[93],"system":[95,150],"uses":[96],"combination":[98],"user":[100],"annotations":[101],"raw":[104],"itself":[106],"extract":[108],"context-free":[110,116],"grammar":[111,117],"from":[112],"document.":[114],"This":[115],"can":[118],"then":[119],"be":[120,136,157],"used":[121],"parse":[123,132],"transform":[127],"it":[128],"into":[129,168],"XML":[131],"tree,":[133],"may":[135,156],"viewed":[137],"through":[138],"browser":[140],"analysis":[142],"or":[143,166],"debugging":[144],"purposes.":[145],"addition,":[147],"generates":[151],"PADS/ML":[153],"description,":[154],"saved":[158],"as":[159],"lasting":[160],"compiled":[167],"host":[170],"useful":[172],"tools.":[175]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
