{"id":"https://openalex.org/W2294744884","doi":"https://doi.org/10.1007/978-3-319-25485-2_5","title":"Web as a Corpus: Going Beyond the n-gram","display_name":"Web as a Corpus: Going Beyond the n-gram","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2294744884","doi":"https://doi.org/10.1007/978-3-319-25485-2_5","mag":"2294744884"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-25485-2_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-25485-2_5","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","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/A5012055259","display_name":"Preslav Nakov","orcid":"https://orcid.org/0000-0002-3600-1510"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Preslav Nakov","raw_affiliation_strings":["Qatar Computing Research Institute, Tornado Tower, Floor 10, P.O.box 5825, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Tornado Tower, Floor 10, P.O.box 5825, Doha, Qatar","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012055259"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3414,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58977247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"185","last_page":"228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9977999925613403,"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":0.7777761220932007},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.7218465805053711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.591813325881958},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.550828218460083},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5430540442466736},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5279642343521118},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.5224441885948181},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45640623569488525},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4305010735988617},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.42519518733024597},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24481108784675598},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.21207726001739502},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07675173878669739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777761220932007},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7218465805053711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.591813325881958},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.550828218460083},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5430540442466736},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5279642343521118},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.5224441885948181},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45640623569488525},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4305010735988617},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.42519518733024597},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24481108784675598},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.21207726001739502},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07675173878669739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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":1,"locations":[{"id":"doi:10.1007/978-3-319-25485-2_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-319-25485-2_5","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":101,"referenced_works":["https://openalex.org/W22977213","https://openalex.org/W56220166","https://openalex.org/W73310205","https://openalex.org/W77146693","https://openalex.org/W97622340","https://openalex.org/W99075841","https://openalex.org/W119080155","https://openalex.org/W149643677","https://openalex.org/W198220271","https://openalex.org/W1255655817","https://openalex.org/W1503325527","https://openalex.org/W1516391399","https://openalex.org/W1534247611","https://openalex.org/W1540931780","https://openalex.org/W1550400585","https://openalex.org/W1562687567","https://openalex.org/W1577362947","https://openalex.org/W1584130740","https://openalex.org/W1591380337","https://openalex.org/W1606177486","https://openalex.org/W1632114991","https://openalex.org/W1647729745","https://openalex.org/W1659833910","https://openalex.org/W1733633583","https://openalex.org/W1853442576","https://openalex.org/W1859173823","https://openalex.org/W1949782377","https://openalex.org/W1965977019","https://openalex.org/W1981724541","https://openalex.org/W1983032487","https://openalex.org/W1994563080","https://openalex.org/W1996430422","https://openalex.org/W1998720920","https://openalex.org/W2000577984","https://openalex.org/W2014516359","https://openalex.org/W2015042937","https://openalex.org/W2021307530","https://openalex.org/W2027666258","https://openalex.org/W2038227658","https://openalex.org/W2038721957","https://openalex.org/W2043814069","https://openalex.org/W2059031628","https://openalex.org/W2060779471","https://openalex.org/W2061023833","https://openalex.org/W2062046281","https://openalex.org/W2076002267","https://openalex.org/W2083783479","https://openalex.org/W2098162425","https://openalex.org/W2098801107","https://openalex.org/W2099685860","https://openalex.org/W2099779943","https://openalex.org/W2102967855","https://openalex.org/W2104232304","https://openalex.org/W2106279089","https://openalex.org/W2109664771","https://openalex.org/W2109830295","https://openalex.org/W2112642950","https://openalex.org/W2117424365","https://openalex.org/W2121357917","https://openalex.org/W2124206172","https://openalex.org/W2124416056","https://openalex.org/W2124556666","https://openalex.org/W2132134739","https://openalex.org/W2133322356","https://openalex.org/W2136930489","https://openalex.org/W2141599568","https://openalex.org/W2143017787","https://openalex.org/W2145080939","https://openalex.org/W2146442558","https://openalex.org/W2146882220","https://openalex.org/W2150290224","https://openalex.org/W2150417504","https://openalex.org/W2152358231","https://openalex.org/W2154507487","https://openalex.org/W2157963512","https://openalex.org/W2158551114","https://openalex.org/W2165405828","https://openalex.org/W2167007219","https://openalex.org/W2168341766","https://openalex.org/W2170844210","https://openalex.org/W2181042685","https://openalex.org/W2218844149","https://openalex.org/W2250189634","https://openalex.org/W2250196260","https://openalex.org/W2251723968","https://openalex.org/W2295081780","https://openalex.org/W2383833906","https://openalex.org/W2435251607","https://openalex.org/W2491988859","https://openalex.org/W2618567416","https://openalex.org/W2913179481","https://openalex.org/W2949154782","https://openalex.org/W2951193962","https://openalex.org/W2952951087","https://openalex.org/W2989939775","https://openalex.org/W3013264884","https://openalex.org/W4235505822","https://openalex.org/W4243092698","https://openalex.org/W4254222580","https://openalex.org/W4300718545","https://openalex.org/W6630872052"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W2349635380","https://openalex.org/W2353819554","https://openalex.org/W2359488321","https://openalex.org/W4236073812","https://openalex.org/W3048777016","https://openalex.org/W4237719335"],"abstract_inverted_index":null,"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
