{"id":"https://openalex.org/W2037796960","doi":"https://doi.org/10.1007/s10791-008-9058-8","title":"Focused web crawling in the acquisition of comparable corpora","display_name":"Focused web crawling in the acquisition of comparable corpora","publication_year":2008,"publication_date":"2008-03-14","ids":{"openalex":"https://openalex.org/W2037796960","doi":"https://doi.org/10.1007/s10791-008-9058-8","mag":"2037796960"},"language":"en","primary_location":{"id":"doi:10.1007/s10791-008-9058-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10791-008-9058-8","pdf_url":null,"source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"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":"Information Retrieval","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://trepo.tuni.fi/bitstream/10024/65978/1/focused_web_crawling_2008.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026174345","display_name":"Tuomas Talvensaari","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Tuomas Talvensaari","raw_affiliation_strings":["Department of Computer Sciences, University of Tampere, Kanslerinrinne 1, Tampere, 33014, Finland","Department of Computer Sciences, University of Tampere, Tampere, Finland 33014#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Tampere, Kanslerinrinne 1, Tampere, 33014, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Computer Sciences, University of Tampere, Tampere, Finland 33014#TAB#","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043509852","display_name":"Ari Pirkola","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]},{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ari Pirkola","raw_affiliation_strings":["Department of Information Studies, University of Tampere, Kanslerinrinne 1, Tampere, 33014, Finland","Department of Information Studies, University of Tampere, Tampere, Finland 33014#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Information Studies, University of Tampere, Kanslerinrinne 1, Tampere, 33014, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Information Studies, University of Tampere, Tampere, Finland 33014#TAB#","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014374477","display_name":"Kalervo J\u00e4rvelin","orcid":"https://orcid.org/0000-0001-7655-8930"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kalervo J\u00e4rvelin","raw_affiliation_strings":["Department of Information Studies, University of Tampere, Kanslerinrinne 1, Tampere, 33014, Finland","Department of Information Studies, University of Tampere, Tampere, Finland 33014#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Information Studies, University of Tampere, Kanslerinrinne 1, Tampere, 33014, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Information Studies, University of Tampere, Tampere, Finland 33014#TAB#","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023021257","display_name":"Martti Juhola","orcid":"https://orcid.org/0000-0003-2298-9553"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Martti Juhola","raw_affiliation_strings":["Department of Computer Sciences, University of Tampere, Kanslerinrinne 1, Tampere, 33014, Finland","Department of Computer Sciences, University of Tampere, Tampere, Finland 33014#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Tampere, Kanslerinrinne 1, Tampere, 33014, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Computer Sciences, University of Tampere, Tampere, Finland 33014#TAB#","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084187883","display_name":"Jorma Laurikkala","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]},{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jorma Laurikkala","raw_affiliation_strings":["Department of Computer Sciences, University of Tampere, Kanslerinrinne 1, Tampere, 33014, Finland","Department of Computer Sciences, University of Tampere, Tampere, Finland 33014#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Tampere, Kanslerinrinne 1, Tampere, 33014, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Computer Sciences, University of Tampere, Tampere, Finland 33014#TAB#","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026174345"],"corresponding_institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":6.9982,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.96539037,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"11","issue":"5","first_page":"427","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.998199999332428,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9825999736785889,"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":0.8591858148574829},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7426714897155762},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6482402086257935},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6479476690292358},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5898370146751404},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5488680601119995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5425806641578674},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5339006185531616},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4708791673183441},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4574086666107178},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27257847785949707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8591858148574829},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7426714897155762},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6482402086257935},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6479476690292358},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5898370146751404},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5488680601119995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5425806641578674},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5339006185531616},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4708791673183441},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4574086666107178},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27257847785949707},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10791-008-9058-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10791-008-9058-8","pdf_url":null,"source":{"id":"https://openalex.org/S79460864","display_name":"Information Retrieval","issn_l":"1386-4564","issn":["1386-4564","1573-7659"],"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":"Information Retrieval","raw_type":"journal-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/65978","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/65978","pdf_url":"https://trepo.tuni.fi/bitstream/10024/65978/1/focused_web_crawling_2008.pdf","source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:tampub.uta.fi:10024/65978","is_oa":false,"landing_page_url":"http://tampub.uta.fi/handle/10024/65978","pdf_url":null,"source":{"id":"https://openalex.org/S4306401860","display_name":"Tampere University Institutional Repository (Tampere University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I150589677","host_organization_name":"Tampere University of Applied Sciences","host_organization_lineage":["https://openalex.org/I150589677"],"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":{"id":"pmh:oai:trepo.tuni.fi:10024/65978","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/65978","pdf_url":"https://trepo.tuni.fi/bitstream/10024/65978/1/focused_web_crawling_2008.pdf","source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2037796960.pdf","grobid_xml":"https://content.openalex.org/works/W2037796960.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W150793826","https://openalex.org/W173995639","https://openalex.org/W1489181569","https://openalex.org/W1489992655","https://openalex.org/W1497067520","https://openalex.org/W1533946607","https://openalex.org/W1555108314","https://openalex.org/W1562514231","https://openalex.org/W1599955416","https://openalex.org/W1625582487","https://openalex.org/W1976381247","https://openalex.org/W1988900289","https://openalex.org/W2000569744","https://openalex.org/W2002664886","https://openalex.org/W2011833440","https://openalex.org/W2024181699","https://openalex.org/W2029341294","https://openalex.org/W2047959359","https://openalex.org/W2060553481","https://openalex.org/W2093976457","https://openalex.org/W2110577582","https://openalex.org/W2138151602","https://openalex.org/W2138553032","https://openalex.org/W2145080939","https://openalex.org/W2405617275","https://openalex.org/W4234200495","https://openalex.org/W6632118081","https://openalex.org/W6633550561","https://openalex.org/W7021264618"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W4255854114"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
