{"id":"https://openalex.org/W1886927463","doi":"https://doi.org/10.17562/pb-41-2","title":"Semi-Automatic Parallel Corpora Extraction from Comparable News Corpora","display_name":"Semi-Automatic Parallel Corpora Extraction from Comparable News Corpora","publication_year":2010,"publication_date":"2010-06-30","ids":{"openalex":"https://openalex.org/W1886927463","doi":"https://doi.org/10.17562/pb-41-2","mag":"1886927463"},"language":"en","primary_location":{"id":"doi:10.17562/pb-41-2","is_oa":false,"landing_page_url":"https://doi.org/10.17562/pb-41-2","pdf_url":null,"source":{"id":"https://openalex.org/S4210186437","display_name":"Polibits","issn_l":"1870-9044","issn":["1870-9044","2395-8618"],"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":"Polibits","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.redalyc.org/pdf/4026/402640454002.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029923937","display_name":"Thoudam Doren Singh","orcid":"https://orcid.org/0000-0001-9906-9136"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Thoudam Doren Singh","raw_affiliation_strings":["Jadavpur University, Computer Science and Engineering Department, Calcuta, Bengala Occidental, India"],"affiliations":[{"raw_affiliation_string":"Jadavpur University, Computer Science and Engineering Department, Calcuta, Bengala Occidental, India","institution_ids":["https://openalex.org/I170979836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006218020","display_name":"Sivaji Bandyopadhyay","orcid":"https://orcid.org/0000-0003-2607-1774"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sivaji Bandyopadhyay","raw_affiliation_strings":["Jadavpur University, Computer Science and Engineering Department, Calcuta, Bengala Occidental, India"],"affiliations":[{"raw_affiliation_string":"Jadavpur University, Computer Science and Engineering Department, Calcuta, Bengala Occidental, India","institution_ids":["https://openalex.org/I170979836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029923937"],"corresponding_institution_ids":["https://openalex.org/I170979836"],"apc_list":null,"apc_paid":null,"fwci":1.8042,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86366929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"41","issue":null,"first_page":"11","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9962999820709229,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6373427510261536},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6260620951652527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5678284764289856},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5000209808349609},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.4787518382072449},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.22702807188034058},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11372169852256775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6373427510261536},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6260620951652527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5678284764289856},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5000209808349609},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4787518382072449},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.22702807188034058},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11372169852256775},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.17562/pb-41-2","is_oa":false,"landing_page_url":"https://doi.org/10.17562/pb-41-2","pdf_url":null,"source":{"id":"https://openalex.org/S4210186437","display_name":"Polibits","issn_l":"1870-9044","issn":["1870-9044","2395-8618"],"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":"Polibits","raw_type":"journal-article"},{"id":"pmh:oai:redalyc.org:402640454002","is_oa":true,"landing_page_url":"https://www.redalyc.org/articulo.oa?id=402640454002","pdf_url":"https://www.redalyc.org/pdf/4026/402640454002.pdf","source":{"id":"https://openalex.org/S4377196100","display_name":"Redalyc (Universidad Aut\u00f3noma del Estado de M\u00e9xico)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I179647637","host_organization_name":"Universidad Aut\u00f3noma del Estado de M\u00e9xico","host_organization_lineage":["https://openalex.org/I179647637"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Polibits (M\u00e9xico) Vol.41","raw_type":"art\u00edculo cient\u00edfico"}],"best_oa_location":{"id":"pmh:oai:redalyc.org:402640454002","is_oa":true,"landing_page_url":"https://www.redalyc.org/articulo.oa?id=402640454002","pdf_url":"https://www.redalyc.org/pdf/4026/402640454002.pdf","source":{"id":"https://openalex.org/S4377196100","display_name":"Redalyc (Universidad Aut\u00f3noma del Estado de M\u00e9xico)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I179647637","host_organization_name":"Universidad Aut\u00f3noma del Estado de M\u00e9xico","host_organization_lineage":["https://openalex.org/I179647637"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Polibits (M\u00e9xico) Vol.41","raw_type":"art\u00edculo cient\u00edfico"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1886927463.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W9407926","https://openalex.org/W22168010","https://openalex.org/W1451039621","https://openalex.org/W1489181569","https://openalex.org/W1491634991","https://openalex.org/W1499134405","https://openalex.org/W2006969979","https://openalex.org/W2042858945","https://openalex.org/W2110240592","https://openalex.org/W2111885854","https://openalex.org/W2115755647","https://openalex.org/W2117652747","https://openalex.org/W2138584836","https://openalex.org/W2138871615","https://openalex.org/W2166098990","https://openalex.org/W2168929382","https://openalex.org/W2170962993","https://openalex.org/W2277993829","https://openalex.org/W3196880344"],"related_works":["https://openalex.org/W3123064333","https://openalex.org/W2143927888","https://openalex.org/W2242707303","https://openalex.org/W2757753881","https://openalex.org/W2123678043","https://openalex.org/W2125885330","https://openalex.org/W2902262852","https://openalex.org/W37319627","https://openalex.org/W1572297637","https://openalex.org/W2251265917"],"abstract_inverted_index":{"\"The":[0],"parallel":[1,28,49],"corpus":[2,29,50],"is":[3,111,119],"a":[4,42,53,64],"necessary":[5],"resource":[6,57,161],"in":[7,90,123,129,154],"many":[8],"multi/cross":[9],"lingual":[10],"natural":[11],"language":[12,60,156],"processing":[13],"applications":[14],"that":[15,47,131],"include":[16],"Machine":[17],"Translation":[18],"and":[19,32,56,61,78,88,100,141,164],"Cross":[20],"Lingual":[21],"Information":[22],"Retreival.":[23],"Preparation":[24],"of":[25,81,117],"large":[26],"scale":[27],"takes":[30],"time":[31],"also":[33,145],"demands":[34],"the":[35,39,70,91,98,104,133],"linguistics":[36],"skill.":[37],"In":[38],"present":[40,92],"work,":[41],"technique":[43,150],"has":[44,138,144],"been":[45,86,139,146],"developed":[46,87],"extracts":[48],"between":[51],"Manipuri,":[52],"morphologically":[54],"rich":[55],"constrained":[58],"Indian":[59,166],"English":[62],"from":[63,69],"comparable":[65],"news":[66],"corpora":[67],"collected":[68],"web.":[71],"A":[72,114],"medium":[73],"sized":[74],"Manipuri-English":[75,82,155],"bilingual":[76],"lexicon":[77],"another":[79],"list":[80],"transliterated":[83],"entities":[84],"have":[85],"used":[89],"work.":[93],"Using":[94],"morphological":[95],"information":[96],"for":[97],"agglutinative":[99,163],"in\ufb02ective":[101,165],"Manipuri":[102],"language,":[103],"alignment":[105,125],"quality":[106],"based":[107],"on":[108],"similarity":[109],"measure":[110],"further":[112,127],"improved.":[113],"high":[115],"level":[116],"performance":[118],"desirable":[120],"since":[121],"errors":[122,128],"sentence":[124],"cause":[126],"systems":[130],"use":[132],"aligned":[134],"text.":[135],"The":[136,149],"system":[137],"evaluated":[140],"error":[142],"analysis":[143],"carried":[147],"out.":[148],"shows":[151],"its":[152],"effectiveness":[153],"pairandis":[157],"extendable":[158],"to":[159],"other":[160],"constrained,":[162],"languages.\"":[167]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}