{"id":"https://openalex.org/W98191119","doi":"https://doi.org/10.3233/978-1-60750-641-6-161","title":"A Collection of Comparable Corpora for Under-resourced Languages","display_name":"A Collection of Comparable Corpora for Under-resourced Languages","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W98191119","doi":"https://doi.org/10.3233/978-1-60750-641-6-161","mag":"98191119"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-60750-641-6-161","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-60750-641-6-161","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"Frontiers in Artificial Intelligence and Applications","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":null,"display_name":"Skadi&ncedil;a Inguna","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146923","display_name":"Tilde (Latvia)","ror":"https://ror.org/03jcesj83","country_code":"LV","type":"company","lineage":["https://openalex.org/I4210146923"]}],"countries":["LV"],"is_corresponding":true,"raw_author_name":"Skadi&ncedil;a Inguna","raw_affiliation_strings":["Tilde, Latvia#TAB#"],"affiliations":[{"raw_affiliation_string":"Tilde, Latvia#TAB#","institution_ids":["https://openalex.org/I4210146923"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065296262","display_name":"Ahmet Aker","orcid":"https://orcid.org/0000-0003-3381-0790"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aker Ahmet","raw_affiliation_strings":["University of sheffield, UK"],"affiliations":[{"raw_affiliation_string":"University of sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042878168","display_name":"Voula Giouli","orcid":"https://orcid.org/0000-0002-1501-9754"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Giouli Voula","raw_affiliation_strings":["Institute for Language and Speech Processing, R.C. \u201cAthena\u201d, Greece#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing, R.C. \u201cAthena\u201d, Greece#TAB#","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062940611","display_name":"Dan Tufi\u015f","orcid":"https://orcid.org/0000-0002-8280-9852"},"institutions":[{"id":"https://openalex.org/I58077936","display_name":"Romanian Academy","ror":"https://ror.org/0561n6946","country_code":"RO","type":"archive","lineage":["https://openalex.org/I58077936"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Tufis Dan","raw_affiliation_strings":["Research Institute for Artificial Intelligence, Romanian Academy Bucharest, Romania#TAB#"],"affiliations":[{"raw_affiliation_string":"Research Institute for Artificial Intelligence, Romanian Academy Bucharest, Romania#TAB#","institution_ids":["https://openalex.org/I58077936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040587162","display_name":"Robert Gaizauskas","orcid":"https://orcid.org/0000-0002-3356-5126"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gaizauskas Robert","raw_affiliation_strings":["University of sheffield, UK"],"affiliations":[{"raw_affiliation_string":"University of sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mieri&ncedil;a Madara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146923","display_name":"Tilde (Latvia)","ror":"https://ror.org/03jcesj83","country_code":"LV","type":"company","lineage":["https://openalex.org/I4210146923"]}],"countries":["LV"],"is_corresponding":false,"raw_author_name":"Mieri&ncedil;a Madara","raw_affiliation_strings":["Tilde, Latvia#TAB#"],"affiliations":[{"raw_affiliation_string":"Tilde, Latvia#TAB#","institution_ids":["https://openalex.org/I4210146923"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045614251","display_name":"Nikos Mastropavlos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Mastropavlos Nikos","raw_affiliation_strings":["Institute for Language and Speech Processing, R.C. \u201cAthena\u201d, Greece#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute for Language and Speech Processing, R.C. \u201cAthena\u201d, Greece#TAB#","institution_ids":["https://openalex.org/I4210098364"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210146923"],"apc_list":null,"apc_paid":null,"fwci":2.8268,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91080854,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"168"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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":0.44410067796707153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41991788148880005},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.38521474599838257},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.3352496922016144},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09562951326370239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44410067796707153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41991788148880005},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.38521474599838257},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.3352496922016144},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09562951326370239}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-60750-641-6-161","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-60750-641-6-161","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"mag:98191119","is_oa":false,"landing_page_url":"https://www.ilsp.gr/homepages/docs/1-skadina-2010.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W10032143","https://openalex.org/W84079877","https://openalex.org/W635530177","https://openalex.org/W1586660424","https://openalex.org/W1625582487","https://openalex.org/W2029341294","https://openalex.org/W2066651136","https://openalex.org/W2107695330","https://openalex.org/W2149366535","https://openalex.org/W2153488166"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"work":[3,26],"on":[4],"collecting":[5],"comparable":[6,68],"corpora":[7,97,104],"for":[8,74,93,110],"9":[9],"language":[10],"pairs:":[11],"Estonian-English,":[12],"Latvian-English,":[13],"Lithuanian-English,":[14],"Greek-English,":[15],"Greek-Romanian,":[16],"Croatian-English,":[17],"Romanian-English,":[18],"Romanian-German":[19],"and":[20,35,37,56,62],"Slovenian-English.":[21],"The":[22,100],"objective":[23],"of":[24,42,58,102],"this":[25],"was":[27],"to":[28,46,67,70],"gather":[29],"texts":[30,69],"from":[31,88],"the":[32,82],"same":[33],"domains":[34],"genres":[36],"with":[38],"a":[39,50],"similar":[40],"level":[41],"comparability":[43],"in":[44,53,76,81],"order":[45],"use":[47,75],"them":[48],"as":[49],"starting":[51],"point":[52],"defining":[54],"criteria":[55,61],"metrics":[57,63],"comparability.":[59],"These":[60],"will":[64],"be":[65],"applied":[66],"determine":[71],"their":[72],"suitability":[73],"Statistical":[77],"Machine":[78],"Translation,":[79],"particularly":[80],"case":[83],"where":[84],"translation":[85],"is":[86,105],"performed":[87],"or":[89],"into":[90],"under-resourced":[91,112],"languages":[92],"which":[94],"substantial":[95],"parallel":[96],"are":[98],"unavailable.":[99],"size":[101],"collected":[103],"about":[106],"1":[107],"million":[108],"words":[109],"each":[111],"language.":[113]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2016-06-24T00:00:00"}
