{"id":"https://openalex.org/W1976381247","doi":"https://doi.org/10.1145/1198296.1198300","title":"Creating and exploiting a comparable corpus in cross-language information retrieval","display_name":"Creating and exploiting a comparable corpus in cross-language information retrieval","publication_year":2007,"publication_date":"2007-02-01","ids":{"openalex":"https://openalex.org/W1976381247","doi":"https://doi.org/10.1145/1198296.1198300","mag":"1976381247"},"language":"en","primary_location":{"id":"doi:10.1145/1198296.1198300","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1198296.1198300","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://trepo.tuni.fi/bitstream/10024/66015/1/creating_and_exploiting_a_comparable_corpus_2007.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":false,"raw_author_name":"Tuomas Talvensaari","raw_affiliation_strings":["University of Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084187883","display_name":"Jorma Laurikkala","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":false,"raw_author_name":"Jorma Laurikkala","raw_affiliation_strings":["University of Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tampere, Finland","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":["University of Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tampere, Finland","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":["University of Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074159111","display_name":"Heikki Keskustalo","orcid":"https://orcid.org/0000-0003-1415-373X"},"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":"Heikki Keskustalo","raw_affiliation_strings":["University of Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.725,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.95664657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"25","issue":"1","first_page":"4","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9965000152587891,"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":0.9930999875068665,"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":0.8897887468338013},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6600037217140198},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6434881687164307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5118814706802368},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5049970746040344},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49312612414360046},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.4438473582267761},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.43423986434936523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8897887468338013},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6600037217140198},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6434881687164307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5118814706802368},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5049970746040344},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49312612414360046},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.4438473582267761},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.43423986434936523},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1198296.1198300","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1198296.1198300","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/66015","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/66015","pdf_url":"https://trepo.tuni.fi/bitstream/10024/66015/1/creating_and_exploiting_a_comparable_corpus_2007.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:10024/66015","is_oa":false,"landing_page_url":"http://tampub.uta.fi/handle/10024/66015","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:10024/66015","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/66015","pdf_url":"https://trepo.tuni.fi/bitstream/10024/66015/1/creating_and_exploiting_a_comparable_corpus_2007.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","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1976381247.pdf","grobid_xml":"https://content.openalex.org/works/W1976381247.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W48945287","https://openalex.org/W51309311","https://openalex.org/W103650626","https://openalex.org/W118616377","https://openalex.org/W160477930","https://openalex.org/W201288405","https://openalex.org/W283200890","https://openalex.org/W311963822","https://openalex.org/W1500117362","https://openalex.org/W1540719499","https://openalex.org/W1543039027","https://openalex.org/W1555108314","https://openalex.org/W1562514231","https://openalex.org/W1599955416","https://openalex.org/W1884973656","https://openalex.org/W1956559956","https://openalex.org/W1971285215","https://openalex.org/W1985987256","https://openalex.org/W2000569744","https://openalex.org/W2001671892","https://openalex.org/W2011833440","https://openalex.org/W2018378073","https://openalex.org/W2041232209","https://openalex.org/W2044490427","https://openalex.org/W2047959359","https://openalex.org/W2050879758","https://openalex.org/W2056989505","https://openalex.org/W2081477775","https://openalex.org/W2093976457","https://openalex.org/W2094737019","https://openalex.org/W2097835057","https://openalex.org/W2138553032","https://openalex.org/W2145080939","https://openalex.org/W2161935199","https://openalex.org/W2295267964","https://openalex.org/W2312704740","https://openalex.org/W2726585279","https://openalex.org/W4234200495","https://openalex.org/W4282942943","https://openalex.org/W4302780227","https://openalex.org/W6640862754","https://openalex.org/W7009000405"],"related_works":["https://openalex.org/W2376554757","https://openalex.org/W612150824","https://openalex.org/W2361959990","https://openalex.org/W1596512750","https://openalex.org/W2383443050","https://openalex.org/W2367702734","https://openalex.org/W2100945520","https://openalex.org/W2386525189","https://openalex.org/W2360284199","https://openalex.org/W2359614599"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,6,30,36,41,85,123,131],"method":[3],"for":[4],"creating":[5],"comparable":[7,31,118],"text":[8],"corpus":[9,32,144],"from":[10,33,52],"two":[11],"document":[12],"collections":[13,18],"in":[14,23],"different":[15,22],"languages.":[16],"The":[17,44,70,90,116,134],"can":[19],"be":[20],"very":[21],"origin.":[24],"In":[25],"this":[26],"study,":[27],"we":[28],"build":[29],"articles":[34],"by":[35,61],"Swedish":[37],"news":[38],"agency":[39],"and":[40,99,112],"U.S.":[42],"newspaper.":[43],"keys":[45,71],"with":[46,84,130],"best":[47],"resolution":[48],"power":[49],"were":[50,72,93],"extracted":[51],"the":[53,58,63,75,78,81,96,106],"documents":[54,108],"of":[55,77],"one":[56],"collection,":[57,60,80,83],"source":[59],"using":[62],"relative":[64],"average":[65],"term":[66],"frequency":[67],"(RATF)":[68],"value.":[69],"translated":[73,91],"into":[74],"language":[76],"other":[79],"target":[82,97],"dictionary-based":[86,132,141],"query":[87],"translation":[88,138,142,145],"program.":[89],"queries":[92,128],"run":[94],"against":[95],"collection":[98,119],"an":[100],"alignment":[101],"pair":[102],"was":[103,120,146],"made":[104],"if":[105],"retrieved":[107],"matched":[109],"given":[110],"date":[111],"similarity":[113,124],"score":[114],"criteria.":[115],"resulting":[117],"used":[121,147],"as":[122],"thesaurus":[125],"to":[126],"translate":[127],"along":[129],"translator.":[133],"combined":[135],"approaches":[136],"outperformed":[137],"schemes":[139],"where":[140],"or":[143],"alone.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
