{"id":"https://openalex.org/W4402081394","doi":"https://doi.org/10.1007/978-3-031-70563-2_5","title":"The Aranea Corpora Family: Ten+ Years of\u00a0Processing Web-Crawled Data","display_name":"The Aranea Corpora Family: Ten+ Years of\u00a0Processing Web-Crawled Data","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402081394","doi":"https://doi.org/10.1007/978-3-031-70563-2_5"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-70563-2_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-70563-2_5","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":"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/A5032717207","display_name":"\u0412\u043b\u0430\u0434\u0438\u043c\u0438\u0440 \u0411\u0435\u043d\u043a\u043e","orcid":"https://orcid.org/0000-0002-4600-5515"},"institutions":[{"id":"https://openalex.org/I4210158485","display_name":"Ludovit Stur Institute of Linguistics of the Slovak Academy of Sciences","ror":"https://ror.org/0517k6d93","country_code":"SK","type":"facility","lineage":["https://openalex.org/I207624831","https://openalex.org/I4210158485"]},{"id":"https://openalex.org/I74788687","display_name":"Comenius University Bratislava","ror":"https://ror.org/0587ef340","country_code":"SK","type":"education","lineage":["https://openalex.org/I74788687"]}],"countries":["SK"],"is_corresponding":true,"raw_author_name":"Vladim\u00edr Benko","raw_affiliation_strings":["Comenius University Science Park, UNESCO Chair in Plurilingual and Multicultural Communications, Ilkovi\u010dova 8, 814 04, Bratislava, Slovakia","Slovak Academy of Sciences, \u013d. \u0160t\u00far Institute of Linguistics, Pansk\u00e1 26, 811 011, Bratislava, Slovakia"],"raw_orcid":"https://orcid.org/0000-0002-4600-5515","affiliations":[{"raw_affiliation_string":"Comenius University Science Park, UNESCO Chair in Plurilingual and Multicultural Communications, Ilkovi\u010dova 8, 814 04, Bratislava, Slovakia","institution_ids":["https://openalex.org/I74788687"]},{"raw_affiliation_string":"Slovak Academy of Sciences, \u013d. \u0160t\u00far Institute of Linguistics, Pansk\u00e1 26, 811 011, Bratislava, Slovakia","institution_ids":["https://openalex.org/I4210158485"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5032717207"],"corresponding_institution_ids":["https://openalex.org/I4210158485","https://openalex.org/I74788687"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":2.2469,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.88936782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9979000091552734,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8598958849906921},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3999727666378021},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38897407054901123},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3564959168434143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34431856870651245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8598958849906921},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3999727666378021},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38897407054901123},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3564959168434143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34431856870651245}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-70563-2_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-70563-2_5","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W331019419","https://openalex.org/W1986330201","https://openalex.org/W2080637049","https://openalex.org/W2124966964","https://openalex.org/W2141457256","https://openalex.org/W2155870214","https://openalex.org/W2252238828","https://openalex.org/W2252262936","https://openalex.org/W3106191616","https://openalex.org/W3207219723","https://openalex.org/W6731765786"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}
