{"id":"https://openalex.org/W2152061679","doi":"https://doi.org/10.1145/1321211.1321246","title":"Removing manually generated boilerplate from electronic texts","display_name":"Removing manually generated boilerplate from electronic texts","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2152061679","doi":"https://doi.org/10.1145/1321211.1321246","mag":"2152061679"},"language":"en","primary_location":{"id":"doi:10.1145/1321211.1321246","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1321211.1321246","pdf_url":null,"source":{"id":"https://openalex.org/S4210189159","display_name":"Proceedings of CASCON","issn_l":"1705-7345","issn":["1705-7345","1705-7353","1705-7361"],"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 2007 conference of the center for advanced studies on Collaborative research - CASCON '07","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5058730847","display_name":"Owen Kaser","orcid":"https://orcid.org/0000-0001-6204-5085"},"institutions":[{"id":"https://openalex.org/I106938459","display_name":"University of New Brunswick","ror":"https://ror.org/05nkf0n29","country_code":"CA","type":"education","lineage":["https://openalex.org/I106938459"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Owen Kaser","raw_affiliation_strings":["University of New Brunswick"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New Brunswick","institution_ids":["https://openalex.org/I106938459"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045561693","display_name":"Daniel Lemire","orcid":"https://orcid.org/0000-0003-3306-6922"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Daniel Lemire","raw_affiliation_strings":["Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","institution_ids":["https://openalex.org/I159129438"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"272","last_page":"272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9991000294685364,"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/T10260","display_name":"Software Engineering Research","score":0.9991000294685364,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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":0.8740535974502563},{"id":"https://openalex.org/keywords/boilerplate-text","display_name":"Boilerplate text","score":0.7276151180267334},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7239544987678528},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6344817876815796},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.6187390089035034},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5929808020591736},{"id":"https://openalex.org/keywords/ascii","display_name":"ASCII","score":0.4547942280769348},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3336350917816162},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3120890259742737},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2423255443572998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8740535974502563},{"id":"https://openalex.org/C75701414","wikidata":"https://www.wikidata.org/wiki/Q1651672","display_name":"Boilerplate text","level":2,"score":0.7276151180267334},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7239544987678528},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6344817876815796},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.6187390089035034},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5929808020591736},{"id":"https://openalex.org/C196832560","wikidata":"https://www.wikidata.org/wiki/Q8815","display_name":"ASCII","level":2,"score":0.4547942280769348},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3336350917816162},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3120890259742737},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2423255443572998}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1321211.1321246","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1321211.1321246","pdf_url":null,"source":{"id":"https://openalex.org/S4210189159","display_name":"Proceedings of CASCON","issn_l":"1705-7345","issn":["1705-7345","1705-7353","1705-7361"],"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 2007 conference of the center for advanced studies on Collaborative research - CASCON '07","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W10423024","https://openalex.org/W151938044","https://openalex.org/W1576259065","https://openalex.org/W1675727887","https://openalex.org/W2006355640","https://openalex.org/W2015201047","https://openalex.org/W2049781914","https://openalex.org/W2064710146","https://openalex.org/W2086017131","https://openalex.org/W2111295912","https://openalex.org/W2113139394","https://openalex.org/W2113757720","https://openalex.org/W2117209866","https://openalex.org/W2150045644","https://openalex.org/W2167973519","https://openalex.org/W2295218488","https://openalex.org/W3101647379"],"related_works":["https://openalex.org/W3121258117","https://openalex.org/W4379160565","https://openalex.org/W629813691","https://openalex.org/W2146642953","https://openalex.org/W2507103705","https://openalex.org/W4210431233","https://openalex.org/W50124057","https://openalex.org/W2953970501","https://openalex.org/W2161402666","https://openalex.org/W3125778814"],"abstract_inverted_index":{"Collaborative":[0],"work":[1],"on":[2,53,72],"unstructured":[3],"or":[4,12,101],"semi-structured":[5],"documents,":[6],"such":[7],"as":[8,45],"in":[9,88],"literature":[10],"corpora":[11],"source":[13],"code,":[14],"often":[15,97],"involves":[16],"agreed":[17],"upon":[18],"templates":[19,23,36],"containing":[20],"metadata.":[21],"These":[22],"are":[24,48,87,96],"not":[25],"consistent":[26],"across":[27],"users":[28],"and":[29,41,93,99],"over":[30],"time.":[31],"Rule-based":[32],"parsing":[33],"of":[34,65,79,119],"these":[35],"is":[37],"expensive":[38],"to":[39,43,59,132],"maintain":[40],"tends":[42],"fail":[44],"new":[46],"documents":[47,86,116],"added.":[49],"Statistical":[50],"techniques":[51],"based":[52],"frequent":[54],"occurrences":[55],"have":[56],"the":[57,66,70,73,77,80],"potential":[58],"identify":[60],"automatically":[61],"a":[62,107],"large":[63,133],"fraction":[64],"templates,":[67],"thus":[68],"reducing":[69],"burden":[71],"programmers.":[74],"We":[75,104,121],"investigate":[76],"case":[78],"Project":[81],"Gutenberg\u2122":[82],"corpus,":[83],"where":[84],"most":[85,112],"ASCII":[89],"format":[90],"with":[91],"preambles":[92],"epilogues":[94],"that":[95,106,127],"copied":[98],"pasted":[100],"manually":[102],"typed.":[103],"show":[105],"statistical":[108],"approach":[109,130],"can":[110],"solve":[111],"cases":[113],"though":[114],"some":[115],"require":[117],"knowledge":[118],"English.":[120],"also":[122],"survey":[123],"various":[124],"technical":[125],"solutions":[126],"make":[128],"our":[129],"applicable":[131],"data":[134],"sets.":[135]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
