{"id":"https://openalex.org/W6907206886","doi":"https://doi.org/10.21227/gz0b-5p24","title":"SUPara0.8M: A Balanced English-Bangla Parallel Corpus","display_name":"SUPara0.8M: A Balanced English-Bangla Parallel Corpus","publication_year":2018,"publication_date":"2018-08-02","ids":{"openalex":"https://openalex.org/W6907206886","doi":"https://doi.org/10.21227/gz0b-5p24"},"language":"en","primary_location":{"id":"doi:10.21227/gz0b-5p24","is_oa":true,"landing_page_url":"https://doi.org/10.21227/gz0b-5p24","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21227/gz0b-5p24","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mumin, M. A. A.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mumin, M. A. A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Seddiqui, M. H.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seddiqui, M. H.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Iqbal, M. Z.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iqbal, M. Z.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Islam, M. J.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Islam, M. J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.715399980545044},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.5909000039100647},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5812000036239624},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5705999732017517},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.45570001006126404},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.45260000228881836},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.3686000108718872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728999853134155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7307999730110168},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.715399980545044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6948999762535095},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.5909000039100647},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5812000036239624},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5705999732017517},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.45570001006126404},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.45260000228881836},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3630000054836273},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/gz0b-5p24","is_oa":true,"landing_page_url":"https://doi.org/10.21227/gz0b-5p24","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.21227/gz0b-5p24","is_oa":true,"landing_page_url":"https://doi.org/10.21227/gz0b-5p24","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.855471670627594}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,64],"dataset":[1,17],"contains":[2],"70,614":[3],"English-Bangla":[4],"sentence":[5],"pairs":[6],"and":[7,32,43,58,79],"more":[8],"than":[9],"0.8":[10],"million":[11],"tokens":[12],"in":[13,61],"each":[14],"side.":[15],"The":[16],"consists":[18],"of":[19,74],"texts":[20,33],"from":[21,40],"different":[22],"genres":[23],"like":[24],"literature,":[25],"journalistic":[26],"texts,":[27,29,31],"instructive":[28],"administrative":[30],"treating":[34],"external":[35],"communication,":[36],"which":[37],"are":[38],"collected":[39],"various":[41,75],"printed":[42],"online":[44],"media.The":[45],"corpus":[46,65],"can":[47,66],"be":[48,68],"used":[49,69],"to":[50,70],"train":[51],"data-driven":[52],"machine":[53],"translation":[54],"system":[55],"between":[56,77],"English":[57,78],"Bangla":[59,80],"languages":[60],"both":[62],"directions.":[63],"also":[67],"perform":[71],"contrastive":[72],"analysis":[73],"features":[76],"languages.":[81]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}
