{"id":"https://openalex.org/W4211234867","doi":"https://doi.org/10.2200/s00508ed1v01y201305hlt022","title":"Web Corpus Construction","display_name":"Web Corpus Construction","publication_year":2013,"publication_date":"2013-07-19","ids":{"openalex":"https://openalex.org/W4211234867","doi":"https://doi.org/10.2200/s00508ed1v01y201305hlt022"},"language":"en","primary_location":{"id":"doi:10.2200/s00508ed1v01y201305hlt022","is_oa":false,"landing_page_url":"https://doi.org/10.2200/s00508ed1v01y201305hlt022","pdf_url":null,"source":{"id":"https://openalex.org/S4210203380","display_name":"Synthesis lectures on human language technologies","issn_l":"1947-4040","issn":["1947-4040","1947-4059"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322570","host_organization_name":"Morgan & Claypool Publishers","host_organization_lineage":["https://openalex.org/P4310322570"],"host_organization_lineage_names":["Morgan & Claypool Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Synthesis Lectures on Human Language Technologies","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/A5070016260","display_name":"Roland Sch\u00e4fer","orcid":"https://orcid.org/0000-0003-3233-7874"},"institutions":[{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Roland Sch\u00e4fer","raw_affiliation_strings":["Freie Universit\u00e4t Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freie Universit\u00e4t Berlin, Germany","institution_ids":["https://openalex.org/I75951250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038109633","display_name":"Felix Bildhauer","orcid":"https://orcid.org/0000-0002-6567-5987"},"institutions":[{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Bildhauer","raw_affiliation_strings":["Freie Universit\u00e4t Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Freie Universit\u00e4t Berlin, Germany","institution_ids":["https://openalex.org/I75951250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75951250"],"apc_list":null,"apc_paid":null,"fwci":11.716,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.98209823,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"6","issue":"4","first_page":"1","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9901000261306763,"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/variety","display_name":"Variety (cybernetics)","score":0.7571350932121277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7422739267349243},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.7118502855300903},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5721564888954163},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5666275024414062},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4193931818008423},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4119721055030823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2899603843688965},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2668479084968567}],"concepts":[{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.7571350932121277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422739267349243},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.7118502855300903},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5721564888954163},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5666275024414062},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4193931818008423},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4119721055030823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2899603843688965},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2668479084968567},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","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},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.2200/s00508ed1v01y201305hlt022","is_oa":false,"landing_page_url":"https://doi.org/10.2200/s00508ed1v01y201305hlt022","pdf_url":null,"source":{"id":"https://openalex.org/S4210203380","display_name":"Synthesis lectures on human language technologies","issn_l":"1947-4040","issn":["1947-4040","1947-4059"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310322570","host_organization_name":"Morgan & Claypool Publishers","host_organization_lineage":["https://openalex.org/P4310322570"],"host_organization_lineage_names":["Morgan & Claypool Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Synthesis Lectures on Human Language Technologies","raw_type":"journal-article"},{"id":"pmh:oai:aleph.bib-bvb.de:BVB01-028952616","is_oa":false,"landing_page_url":"https://doi.org/10.2200/S00508ED1V01Y201305HLT022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"software, multimedia"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":120,"referenced_works":["https://openalex.org/W202361227","https://openalex.org/W1489992655","https://openalex.org/W1509958212","https://openalex.org/W1522263329","https://openalex.org/W1559390466","https://openalex.org/W1566513354","https://openalex.org/W1574901103","https://openalex.org/W1575967963","https://openalex.org/W1598996557","https://openalex.org/W1604574761","https://openalex.org/W1605217017","https://openalex.org/W1608699565","https://openalex.org/W1969301668","https://openalex.org/W1971892934","https://openalex.org/W1974288322","https://openalex.org/W1974715550","https://openalex.org/W1983416950","https://openalex.org/W1989856433","https://openalex.org/W1990508473","https://openalex.org/W1990645831","https://openalex.org/W1993284846","https://openalex.org/W1996430422","https://openalex.org/W1996934732","https://openalex.org/W1998974009","https://openalex.org/W1999478104","https://openalex.org/W2004671457","https://openalex.org/W2006624771","https://openalex.org/W2007687650","https://openalex.org/W2010595692","https://openalex.org/W2012022516","https://openalex.org/W2014516359","https://openalex.org/W2018934112","https://openalex.org/W2019194162","https://openalex.org/W2029341294","https://openalex.org/W2032355794","https://openalex.org/W2033995706","https://openalex.org/W2040075907","https://openalex.org/W2041741339","https://openalex.org/W2042359627","https://openalex.org/W2042432758","https://openalex.org/W2045998703","https://openalex.org/W2049169605","https://openalex.org/W2049921291","https://openalex.org/W2053763809","https://openalex.org/W2057525273","https://openalex.org/W2062237837","https://openalex.org/W2066636486","https://openalex.org/W2066792529","https://openalex.org/W2076008912","https://openalex.org/W2080676333","https://openalex.org/W2085922539","https://openalex.org/W2087198174","https://openalex.org/W2092911974","https://openalex.org/W2096961418","https://openalex.org/W2097704339","https://openalex.org/W2098162425","https://openalex.org/W2099585315","https://openalex.org/W2100974915","https://openalex.org/W2101909884","https://openalex.org/W2103545802","https://openalex.org/W2109469864","https://openalex.org/W2110520505","https://openalex.org/W2113184419","https://openalex.org/W2115054880","https://openalex.org/W2117364574","https://openalex.org/W2118020653","https://openalex.org/W2120101509","https://openalex.org/W2120511087","https://openalex.org/W2120770606","https://openalex.org/W2121545956","https://openalex.org/W2121764873","https://openalex.org/W2123845384","https://openalex.org/W2124416056","https://openalex.org/W2127973959","https://openalex.org/W2129271949","https://openalex.org/W2133058591","https://openalex.org/W2133322356","https://openalex.org/W2133990480","https://openalex.org/W2135843243","https://openalex.org/W2137135938","https://openalex.org/W2140208587","https://openalex.org/W2140798747","https://openalex.org/W2143230354","https://openalex.org/W2144211451","https://openalex.org/W2148822332","https://openalex.org/W2151007976","https://openalex.org/W2152805927","https://openalex.org/W2153330999","https://openalex.org/W2155711776","https://openalex.org/W2155870214","https://openalex.org/W2158601853","https://openalex.org/W2158997610","https://openalex.org/W2160039544","https://openalex.org/W2164107060","https://openalex.org/W2165345215","https://openalex.org/W2169557227","https://openalex.org/W2169598467","https://openalex.org/W2175110005","https://openalex.org/W2399720833","https://openalex.org/W2420187884","https://openalex.org/W2497265084","https://openalex.org/W4211138600","https://openalex.org/W4211148787","https://openalex.org/W4214671568","https://openalex.org/W4231741839","https://openalex.org/W4232899223","https://openalex.org/W4238346259","https://openalex.org/W4250788613","https://openalex.org/W4300856813","https://openalex.org/W6602210249","https://openalex.org/W6603373351","https://openalex.org/W6632118081","https://openalex.org/W6636631317","https://openalex.org/W6675579160","https://openalex.org/W6679953604","https://openalex.org/W6680963280","https://openalex.org/W6690288713","https://openalex.org/W6739458654","https://openalex.org/W6797424247","https://openalex.org/W7053109615"],"related_works":["https://openalex.org/W3096456556","https://openalex.org/W4240253816","https://openalex.org/W2169584677","https://openalex.org/W2979513934","https://openalex.org/W4232954277","https://openalex.org/W2032233321","https://openalex.org/W2020341030","https://openalex.org/W2749133591","https://openalex.org/W2367473450","https://openalex.org/W23346600"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}