{"id":"https://openalex.org/W2125531260","doi":"https://doi.org/10.1145/1390749.1390762","title":"Data driven methods for improving mono- and cross-lingual IR performance in noisy environments","display_name":"Data driven methods for improving mono- and cross-lingual IR performance in noisy environments","publication_year":2008,"publication_date":"2008-07-24","ids":{"openalex":"https://openalex.org/W2125531260","doi":"https://doi.org/10.1145/1390749.1390762","mag":"2125531260"},"language":"en","primary_location":{"id":"doi:10.1145/1390749.1390762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-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/A5013840360","display_name":"Antti J\u00e4rvelin","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":"Antti J\u00e4rvelin","raw_affiliation_strings":["University of Tampere, Finland"],"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/A5026174345","display_name":"Tuomas Talvensaari","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":"Tuomas Talvensaari","raw_affiliation_strings":["University of Tampere, Finland"],"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/A5000736780","display_name":"Anni J\u00e4rvelin","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":"Anni J\u00e4rvelin","raw_affiliation_strings":["University of Tampere, Finland"],"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":3,"corresponding_author_ids":["https://openalex.org/A5013840360"],"corresponding_institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":0.5721,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78929188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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":0.9966999888420105,"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":0.9937999844551086,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8842591047286987},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6927948594093323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6788084506988525},{"id":"https://openalex.org/keywords/cross-language-information-retrieval","display_name":"Cross-language information retrieval","score":0.5722137093544006},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.44591569900512695},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4191363751888275},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4136471450328827},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3662578761577606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8842591047286987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6927948594093323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6788084506988525},{"id":"https://openalex.org/C2778842860","wikidata":"https://www.wikidata.org/wiki/Q986551","display_name":"Cross-language information retrieval","level":3,"score":0.5722137093544006},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.44591569900512695},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4191363751888275},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4136471450328827},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3662578761577606},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1390749.1390762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322592","display_name":"Tampereen Yliopisto","ror":"https://ror.org/033003e23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W48945287","https://openalex.org/W103650626","https://openalex.org/W120374091","https://openalex.org/W311963822","https://openalex.org/W655715126","https://openalex.org/W1485221229","https://openalex.org/W1536040460","https://openalex.org/W1575218474","https://openalex.org/W1625582487","https://openalex.org/W1660390307","https://openalex.org/W1988900289","https://openalex.org/W2011833440","https://openalex.org/W2018378073","https://openalex.org/W2037796960","https://openalex.org/W2047959359","https://openalex.org/W2060553481","https://openalex.org/W2087447526","https://openalex.org/W2087824626","https://openalex.org/W2093976457","https://openalex.org/W2102712128","https://openalex.org/W2129034170","https://openalex.org/W2137416755","https://openalex.org/W2138151602","https://openalex.org/W2143498478","https://openalex.org/W2149903388","https://openalex.org/W2151858239","https://openalex.org/W2161935199","https://openalex.org/W2168801328","https://openalex.org/W2169048101","https://openalex.org/W2398936787","https://openalex.org/W4302367531","https://openalex.org/W6637101025","https://openalex.org/W6995831674"],"related_works":["https://openalex.org/W2775554247","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613","https://openalex.org/W2296205523"],"abstract_inverted_index":{"In":[0,46,60,114],"cross-language":[1],"information":[2],"retrieval":[3,49],"(CLIR),":[4],"novel":[5],"or":[6,11,25,122],"non-standard":[7],"expressions,":[8],"technical":[9],"terminology,":[10],"rare":[12],"proper":[13],"nouns":[14],"can":[15,100,132],"be":[16,101,133,162],"seen":[17],"as":[18],"noise":[19],"when":[20],"they":[21],"appear":[22],"in":[23,26,152,164],"queries":[24],"the":[27,76,84,104,111,115,118,140,143],"target":[28,105,112],"collection.":[29],"This":[30],"kind":[31],"of":[32,96,142,187],"vocabulary":[33],"is":[34],"often":[35],"out-of-vocabulary":[36],"(OOV)":[37],"for":[38],"dictionaries":[39,168],"that":[40,131],"are":[41,70,125,154,159],"used":[42,134],"to":[43,67,127,135,161],"translate":[44,136],"queries.":[45],"historic":[47],"document":[48,106],"(HDR),":[50],"OCR":[51],"errors":[52],"and":[53,83,108,174,180],"historical":[54],"spelling":[55],"variants":[56],"cause":[57],"similar":[58],"problems.":[59],"this":[61],"paper,":[62],"three":[63,145],"data":[64],"driven":[65],"approaches":[66],"these":[68],"problems":[69],"presented.":[71,156],"The":[72,157],"two":[73],"first":[74],"methods,":[75,144],"transformation":[77],"rule":[78],"based":[79,192],"translation":[80,129,166,178,190],"(TRT)":[81],"method":[82],"classified":[85],"s-gram":[86],"method,":[87,117],"operate":[88],"on":[89],"string":[90],"level.":[91],"With":[92],"them":[93],"approximate":[94],"matches":[95],"a":[97],"query":[98,165],"word":[99,177,189],"recognized":[102],"from":[103],"collection":[107],"included":[109],"into":[110],"query.":[113],"third":[116],"corpus-based":[119],"approach,":[120],"parallel":[121],"comparable":[123],"corpora":[124],"employed":[126],"derive":[128],"knowledge":[130],"OOV":[137,176,188],"words.":[138],"Besides":[139],"overview":[141],"case":[146],"studies":[147],"highlighting":[148],"their":[149],"practical":[150],"applications":[151],"CLIR":[153,183],"also":[155],"methods":[158],"shown":[160],"effective":[163],"without":[167],"between":[169],"closely":[170],"related":[171],"languages":[172],"(TRT":[173],"s-grams),":[175],"(s-grams),":[179],"boosting":[181],"dictionary-based":[182],"performance":[184],"by":[185],"way":[186],"(corpus":[191],"methods).":[193]},"counts_by_year":[{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}