{"id":"https://openalex.org/W658562282","doi":"https://doi.org/10.3115/v1/w14-0402","title":"Focused Web Corpus Crawling","display_name":"Focused Web Corpus Crawling","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W658562282","doi":"https://doi.org/10.3115/v1/w14-0402","mag":"658562282"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-0402","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0402","pdf_url":"https://aclanthology.org/W14-0402.pdf","source":null,"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 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-0402.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070016260","display_name":"Roland Sch\u00e4fer","orcid":"https://orcid.org/0000-0003-3233-7874"},"institutions":[{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Roland Sch\u00e4fer","raw_affiliation_strings":["Freie Universit\u00e4t Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freie Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I75951250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067193631","display_name":"Adrien Barbaresi","orcid":"https://orcid.org/0000-0002-8079-8694"},"institutions":[{"id":"https://openalex.org/I113428412","display_name":"\u00c9cole Normale Sup\u00e9rieure de Lyon","ror":"https://ror.org/04zmssz18","country_code":"FR","type":"education","lineage":["https://openalex.org/I113428412","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I4210120985","display_name":"Institut d'Histoire des Repr\u00e9sentations et des Id\u00e9es dans les Modernit\u00e9s","ror":"https://ror.org/02wmc6m46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I198244214","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210120985","https://openalex.org/I4405259976","https://openalex.org/I874609350"]},{"id":"https://openalex.org/I4210137435","display_name":"Interactions, Corpus, Apprentissages, Repr\u00e9sentations","ror":"https://ror.org/04mn0nr69","country_code":"FR","type":"facility","lineage":["https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210137435"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Adrien Barbaresi","raw_affiliation_strings":["ENS Lyon","Interactions, Corpus, Apprentissages, Repr\u00e9sentations"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ENS Lyon","institution_ids":["https://openalex.org/I4210120985","https://openalex.org/I113428412"]},{"raw_affiliation_string":"Interactions, Corpus, Apprentissages, Repr\u00e9sentations","institution_ids":["https://openalex.org/I4210137435"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038109633","display_name":"Felix Bildhauer","orcid":"https://orcid.org/0000-0002-6567-5987"},"institutions":[{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Bildhauer","raw_affiliation_strings":["Freie Universitt Berlin","Freie Universit\u00e4t Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freie Universitt Berlin","institution_ids":["https://openalex.org/I75951250"]},{"raw_affiliation_string":"Freie Universit\u00e4t Berlin","institution_ids":["https://openalex.org/I75951250"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4611,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.90420492,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9690999984741211,"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/T11478","display_name":"Caching and Content Delivery","score":0.9679999947547913,"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/crawling","display_name":"Crawling","score":0.9395248889923096},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8453677892684937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7925305366516113},{"id":"https://openalex.org/keywords/boilerplate-text","display_name":"Boilerplate text","score":0.6366147994995117},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6077927350997925},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5787946581840515},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4670141339302063}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9395248889923096},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8453677892684937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925305366516113},{"id":"https://openalex.org/C75701414","wikidata":"https://www.wikidata.org/wiki/Q1651672","display_name":"Boilerplate text","level":2,"score":0.6366147994995117},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6077927350997925},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5787946581840515},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4670141339302063},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/w14-0402","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0402","pdf_url":"https://aclanthology.org/W14-0402.pdf","source":null,"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 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-0402","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-0402","pdf_url":"https://aclanthology.org/W14-0402.pdf","source":null,"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 9th Web as Corpus Workshop (WaC-9)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W658562282.pdf","grobid_xml":"https://content.openalex.org/works/W658562282.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1983416950","https://openalex.org/W2064803799","https://openalex.org/W2093418984","https://openalex.org/W2100974915","https://openalex.org/W2110520505","https://openalex.org/W2123845384","https://openalex.org/W2151007976","https://openalex.org/W2155711776","https://openalex.org/W2155870214","https://openalex.org/W2169200297","https://openalex.org/W2188533213","https://openalex.org/W2252238828","https://openalex.org/W2293542752","https://openalex.org/W2737716763","https://openalex.org/W4211234867"],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2964752624","https://openalex.org/W4255854114","https://openalex.org/W2026661369"],"abstract_inverted_index":{"In":[0,100],"web":[1,38,60,63,81,125],"corpus":[2,82,119,126],"construction,":[3],"crawling":[4,26,31,87,122],"is":[5,11,131,146,158],"a":[6,40,156],"necessary":[7],"step,":[8],"and":[9,24,46,97,121],"it":[10,19],"probably":[12],"the":[13,34,37,91,116,138,141,143,149,152],"most":[14],"costly":[15],"of":[16,42,137],"all,":[17],"because":[18],"requires":[20],"expensive":[21],"bandwidth":[22],"usage,":[23],"excess":[25],"increases":[27],"storage":[28],"requirements.":[29],"Excess":[30],"results":[32],"from":[33],"fact":[35],"that":[36,108,151],"contains":[39],"lot":[41],"redundant":[43],"content":[44,89],"(duplicates":[45],"near-duplicates),":[47],"as":[48,50],"well":[49],"other":[51,144],"material":[52],"not":[53],"suitable":[54,113],"or":[55,62,71],"desirable":[56],"for":[57,80,124],"inclusion":[58],"in":[59,90,105],"corpora":[61],"indexes":[64],"(for":[65],"example,":[66],"pages":[67],"with":[68],"little":[69],"text":[70,74,135],"virtually":[72],"no":[73],"at":[75],"all).":[76],"An":[77],"optimized":[78],"crawler":[79],"construction":[83],"would":[84],"ideally":[85],"avoid":[86],"such":[88],"first":[92,129],"place,":[93],"saving":[94],"bandwidth,":[95],"storage,":[96],"post-processing":[98],"costs.":[99],"this":[101],"paper,":[102],"we":[103],"show":[104],"three":[106],"experiments":[107],"two":[109],"simple":[110],"scores":[111],"are":[112],"to":[114,133,148],"improve":[115],"ratio":[117],"between":[118],"size":[120],"effort":[123],"construction.":[127],"The":[128],"score":[130],"related":[132,147],"overall":[134],"quality":[136],"page":[139],"containing":[140],"link,":[142],"one":[145],"likelihood":[150],"local":[153],"block":[154],"enclosing":[155],"link":[157],"boilerplate.":[159]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
