{"id":"https://openalex.org/W2004739122","doi":"https://doi.org/10.1007/s13222-014-0172-z","title":"Internet Corpora: A Challenge for Linguistic Processing","display_name":"Internet Corpora: A Challenge for Linguistic Processing","publication_year":2015,"publication_date":"2015-01-06","ids":{"openalex":"https://openalex.org/W2004739122","doi":"https://doi.org/10.1007/s13222-014-0172-z","mag":"2004739122"},"language":"en","primary_location":{"id":"doi:10.1007/s13222-014-0172-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13222-014-0172-z","pdf_url":null,"source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"type":"article","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/A5072701486","display_name":"Andrea Horbach","orcid":"https://orcid.org/0009-0004-3680-3304"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andrea Horbach","raw_affiliation_strings":["Universit\u00e4t des Saarlandes, Saarbr\u00fccken, Germany","Universitat des Saarlandes, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t des Saarlandes, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Universitat des Saarlandes, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111900696","display_name":"Stefan Thater","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Thater","raw_affiliation_strings":["Universit\u00e4t des Saarlandes, Saarbr\u00fccken, Germany","Universitat des Saarlandes, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t des Saarlandes, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Universitat des Saarlandes, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081875737","display_name":"Diana Steffen","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Diana Steffen","raw_affiliation_strings":["Universit\u00e4t des Saarlandes, Saarbr\u00fccken, Germany","Universitat des Saarlandes, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t des Saarlandes, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Universitat des Saarlandes, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041852883","display_name":"Peter M. Fischer","orcid":"https://orcid.org/0000-0002-5866-9271"},"institutions":[{"id":"https://openalex.org/I4210099471","display_name":"Leibniz Institute for the German Language","ror":"https://ror.org/00hvwkt50","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210099471"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter M. Fischer","raw_affiliation_strings":["IDS, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDS, Mannheim, Germany","institution_ids":["https://openalex.org/I4210099471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035503960","display_name":"Andreas Witt","orcid":"https://orcid.org/0000-0002-0299-5713"},"institutions":[{"id":"https://openalex.org/I4210099471","display_name":"Leibniz Institute for the German Language","ror":"https://ror.org/00hvwkt50","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210099471"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Witt","raw_affiliation_strings":["IDS, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDS, Mannheim, Germany","institution_ids":["https://openalex.org/I4210099471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040513195","display_name":"Manfred Pinkal","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Manfred Pinkal","raw_affiliation_strings":["Universit\u00e4t des Saarlandes, Saarbr\u00fccken, Germany","Universitat des Saarlandes, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t des Saarlandes, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Universitat des Saarlandes, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072701486"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":{"value":2380,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":3.0557,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.92538872,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"15","issue":"1","first_page":"41","last_page":"47"},"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9962000250816345,"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":0.8071850538253784},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.7327102422714233},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6852544546127319},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6240047216415405},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.5617109537124634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.523237407207489},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3807297348976135},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.37079259753227234},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.250663161277771},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.08082389831542969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8071850538253784},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.7327102422714233},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6852544546127319},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6240047216415405},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.5617109537124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.523237407207489},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3807297348976135},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37079259753227234},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.250663161277771},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.08082389831542969},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s13222-014-0172-z","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13222-014-0172-z","pdf_url":null,"source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},{"id":"pmh:oai:ids-pub.bsz-bw.de:4356","is_oa":false,"landing_page_url":"https://ids-pub.bsz-bw.de/frontdoor/index/index/docId/4356","pdf_url":null,"source":{"id":"https://openalex.org/S4306401750","display_name":"Publication Server of the Institute for German Language (Institute for German Language)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210099471","host_organization_name":"Leibniz Institute for the German Language","host_organization_lineage":["https://openalex.org/I4210099471"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W104569075","https://openalex.org/W1631260214","https://openalex.org/W1965364888","https://openalex.org/W1996430422","https://openalex.org/W2052847729","https://openalex.org/W2135843243","https://openalex.org/W2201782030","https://openalex.org/W2250553731","https://openalex.org/W2335306878","https://openalex.org/W2402670915","https://openalex.org/W2404954229","https://openalex.org/W2743407538","https://openalex.org/W4238485333"],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2361959990","https://openalex.org/W2100945520","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W2367702734","https://openalex.org/W644339423","https://openalex.org/W2048048323","https://openalex.org/W2377704837"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
