{"id":"https://openalex.org/W1554954193","doi":"https://doi.org/10.1007/978-3-540-70939-8_4","title":"Conquering Language: Using NLP on a Massive Scale to Build High Dimensional Language Models from the Web","display_name":"Conquering Language: Using NLP on a Massive Scale to Build High Dimensional Language Models from the Web","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W1554954193","doi":"https://doi.org/10.1007/978-3-540-70939-8_4","mag":"1554954193"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-70939-8_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-70939-8_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-01081036","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039513155","display_name":"Gregory Grefenstette","orcid":"https://orcid.org/0000-0001-8479-049X"},"institutions":[{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I4210085861","display_name":"Laboratoire d'Int\u00e9gration des Syst\u00e8mes et des Technologies","ror":"https://ror.org/000dbcc61","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210117989"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Gregory Grefenstette","raw_affiliation_strings":["Commissariat \u00e0 l\u2019Energie Atomique, CEA LIST, SRCI, BP 6, 92265 Fontenay aux Roses Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Commissariat \u00e0 l\u2019Energie Atomique, CEA LIST, SRCI, BP 6, 92265 Fontenay aux Roses Cedex, France","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210085861"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039513155"],"corresponding_institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210085861"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980000257492065,"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/T10028","display_name":"Topic Modeling","score":0.9912999868392944,"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":0.744122326374054},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5885746479034424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.575066089630127},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5181537866592407},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5023503303527832},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4503272771835327},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07310199737548828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744122326374054},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5885746479034424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.575066089630127},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5181537866592407},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5023503303527832},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4503272771835327},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07310199737548828},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-540-70939-8_4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-70939-8_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.475.4262","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.475.4262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://muscle.ercim.eu/images/DocumentPDF/GrefenstettefinalCICLING.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01081036v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01081036","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CICLing, Feb 2007, Mexico, Mexico. pp.35 - 49, ⟨10.1007/978-3-540-70939-8_4⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01081036v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01081036","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CICLing, Feb 2007, Mexico, Mexico. pp.35 - 49, ⟨10.1007/978-3-540-70939-8_4⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W4508078","https://openalex.org/W181231024","https://openalex.org/W1489384387","https://openalex.org/W1533946607","https://openalex.org/W1536026156","https://openalex.org/W1583045132","https://openalex.org/W1593045043","https://openalex.org/W1613836731","https://openalex.org/W1774741270","https://openalex.org/W1859173823","https://openalex.org/W1994563080","https://openalex.org/W2000363133","https://openalex.org/W2024338393","https://openalex.org/W2036373663","https://openalex.org/W2096468639","https://openalex.org/W2103224511","https://openalex.org/W2109464129","https://openalex.org/W2139755556","https://openalex.org/W2144710514","https://openalex.org/W2168625136","https://openalex.org/W2426119782","https://openalex.org/W2504558481","https://openalex.org/W2755866203","https://openalex.org/W4244079188","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2951359407","https://openalex.org/W2124566234","https://openalex.org/W3136979370","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W3204019825"],"abstract_inverted_index":null,"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}