{"id":"https://openalex.org/W2947841048","doi":"https://doi.org/10.3233/978-1-58603-898-4-241","title":"Mining the Web to Build a Complete, Large-Scale Language Model","display_name":"Mining the Web to Build a Complete, Large-Scale Language Model","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2947841048","doi":"https://doi.org/10.3233/978-1-58603-898-4-241","mag":"2947841048"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-58603-898-4-241","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-58603-898-4-241","pdf_url":null,"source":{"id":"https://openalex.org/S4210202636","display_name":"NATO science for peace and security series. D, Information and communication security","issn_l":"1874-6268","issn":["1874-6268","1879-8292"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NATO Science for Peace and Security Series - D: Information and Communication Security","raw_type":"book-chapter"},"type":"book-chapter","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/A5112785976","display_name":"G Gregory","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Grefenstette Gregory","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5112785976"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.248478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9045000076293945,"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":0.9045000076293945,"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":0.6344223022460938},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.581382691860199},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45070549845695496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3674600124359131},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.19132262468338013},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.11704480648040771}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6344223022460938},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.581382691860199},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45070549845695496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3674600124359131},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.19132262468338013},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.11704480648040771}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/978-1-58603-898-4-241","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-58603-898-4-241","pdf_url":null,"source":{"id":"https://openalex.org/S4210202636","display_name":"NATO science for peace and security series. D, Information and communication security","issn_l":"1874-6268","issn":["1874-6268","1879-8292"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NATO Science for Peace and Security Series - D: Information and Communication Security","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"order":[1],"to":[2,33],"detect":[3],"the":[4,20,23,37,84,87],"extraordinary,":[5],"a":[6,10,47,76],"computer":[7],"must":[8],"have":[9],"model":[11,82],"of":[12],"ordinary":[13],"interactions.":[14],"There":[15],"is":[16],"enough":[17],"text":[18,38],"on":[19],"web":[21,85],"in":[22,46,74],"420":[24],"languages":[25,42],"that":[26],"are":[27,57],"represented":[28],"there":[29],"for":[30,40,86],"language":[31,51,81],"models":[32,52],"be":[34,44,64],"built.":[35],"All":[36],"available":[39],"most":[41],"can":[43,53,62],"crawled":[45],"few":[48],"months.":[49],"These":[50],"show":[54],"how":[55],"words":[56],"normally":[58],"associated.":[59],"Unusual":[60],"associations":[61],"then":[63],"detected":[65],"automatically.":[66],"This":[67],"article":[68],"presents":[69],"an":[70],"overview":[71],"our":[72],"work":[73],"building":[75],"very":[77],"large":[78],"and":[79],"complete":[80],"from":[83],"French":[88],"language.":[89]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}