{"id":"https://openalex.org/W2395418806","doi":"https://doi.org/10.3233/978-1-61499-442-8-184","title":"Syntactic N-gram Collection from a Large-Scale Corpus of Internet Finnish","display_name":"Syntactic N-gram Collection from a Large-Scale Corpus of Internet Finnish","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2395418806","doi":"https://doi.org/10.3233/978-1-61499-442-8-184","mag":"2395418806"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-442-8-184","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-442-8-184","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/978-1-61499-442-8-184","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048932608","display_name":"Jenna Kanerva","orcid":"https://orcid.org/0000-0003-4580-5366"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kanerva Jenna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067940433","display_name":"Juhani Luotolahti","orcid":null},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Luotolahti Juhani","raw_affiliation_strings":["University of Turku"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Turku","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036607482","display_name":"Veronika Laippala","orcid":"https://orcid.org/0000-0002-7635-429X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laippala Veronika","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019929457","display_name":"Filip Ginter","orcid":"https://orcid.org/0000-0002-5484-6103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ginter Filip","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8297,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95642662,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","score":0.9918000102043152,"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/n-gram","display_name":"n-gram","score":0.75391685962677},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.7158181667327881},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.562641441822052},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49088674783706665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4871770739555359},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4537612795829773},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.27685776352882385},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25124940276145935},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12398979067802429},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0987909734249115},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.07793980836868286}],"concepts":[{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.75391685962677},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.7158181667327881},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.562641441822052},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49088674783706665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4871770739555359},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4537612795829773},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.27685776352882385},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25124940276145935},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12398979067802429},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0987909734249115},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.07793980836868286},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-61499-442-8-184","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-442-8-184","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"mag:2395418806","is_oa":false,"landing_page_url":"http://w3.erss.univ-tlse2.fr/UETAL/2014-2015/Refs/laippala.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306503995","display_name":"Baltic HLT","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Baltic HLT","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/978-1-61499-442-8-184","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-442-8-184","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.46000000834465027,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W102530743","https://openalex.org/W183066880","https://openalex.org/W1965299982","https://openalex.org/W1986330201","https://openalex.org/W2101244321","https://openalex.org/W2106279089","https://openalex.org/W2117425229","https://openalex.org/W2137471318","https://openalex.org/W2155870214","https://openalex.org/W2189472871","https://openalex.org/W2250837944","https://openalex.org/W2251443999","https://openalex.org/W2251771443","https://openalex.org/W2950577311"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2625039379","https://openalex.org/W2088254117","https://openalex.org/W4254593385","https://openalex.org/W2790582133","https://openalex.org/W1901380241","https://openalex.org/W311963822","https://openalex.org/W2789473152","https://openalex.org/W3132255358"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"report":[4],"on":[5],"the":[6,57,62,71],"development":[7],"of":[8,16,56],"a":[9],"large-scale":[10],"Finnish":[11],"Internet":[12],"parsebank,":[13],"currently":[14],"consisting":[15],"1.5":[17],"billion":[18],"tokens":[19],"in":[20],"116":[21],"million":[22],"sentences.":[23],"The":[24],"data":[25],"is":[26],"fully":[27],"morphologically":[28],"and":[29,32,40,48],"syntactically":[30],"analyzed":[31],"it":[33],"has":[34],"been":[35],"used":[36],"to":[37],"extract":[38],"flat":[39],"syntactic":[41],"n-gram":[42,66],"collections,":[43],"as":[44,46,68,70],"well":[45,69],"verb-argument":[47],"noun-argument":[49],"n-grams.":[50],"Additionally,":[51],"distributional":[52],"vector":[53,72],"space":[54,73],"representations":[55],"words":[58],"are":[59,75],"induced":[60],"using":[61],"word2vec":[63],"method.":[64],"All":[65],"collections":[67],"models":[74],"made":[76],"available":[77],"under":[78],"an":[79],"open":[80],"license.":[81]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
