{"id":"https://openalex.org/W4385572115","doi":"https://doi.org/10.18653/v1/2023.acl-long.115","title":"BIG-C: a Multimodal Multi-Purpose Dataset for Bemba","display_name":"BIG-C: a Multimodal Multi-Purpose Dataset for Bemba","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385572115","doi":"https://doi.org/10.18653/v1/2023.acl-long.115"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.acl-long.115","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.115","pdf_url":"https://aclanthology.org/2023.acl-long.115.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.acl-long.115.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039333739","display_name":"Claytone Sikasote","orcid":"https://orcid.org/0009-0004-1372-4662"},"institutions":[{"id":"https://openalex.org/I33278361","display_name":"University of Zambia","ror":"https://ror.org/03gh19d69","country_code":"ZM","type":"education","lineage":["https://openalex.org/I33278361"]}],"countries":["ZM"],"is_corresponding":true,"raw_author_name":"Claytone Sikasote","raw_affiliation_strings":["Department of Computer Science, University of Zambia, Zambia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Zambia, Zambia","institution_ids":["https://openalex.org/I33278361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080818354","display_name":"Eunice Mukonde","orcid":null},"institutions":[{"id":"https://openalex.org/I33278361","display_name":"University of Zambia","ror":"https://ror.org/03gh19d69","country_code":"ZM","type":"education","lineage":["https://openalex.org/I33278361"]}],"countries":["ZM"],"is_corresponding":false,"raw_author_name":"Eunice Mukonde","raw_affiliation_strings":["Department of Literature and Languages, University of Zambia, Zambia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Literature and Languages, University of Zambia, Zambia","institution_ids":["https://openalex.org/I33278361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005452575","display_name":"Md Mahfuz Ibn Alam","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Mahfuz Ibn Alam","raw_affiliation_strings":["Department of Computer Science, George Mason University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013793053","display_name":"Antonios Anastasopoulos","orcid":"https://orcid.org/0000-0002-8544-246X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonios Anastasopoulos","raw_affiliation_strings":["Department of Computer Science, George Mason University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039333739"],"corresponding_institution_ids":["https://openalex.org/I33278361"],"apc_list":null,"apc_paid":null,"fwci":0.2428,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55947195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2062","last_page":"2078"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9961000084877014,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9915000200271606,"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/T12031","display_name":"Speech and dialogue systems","score":0.9828000068664551,"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":0.8423694372177124},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6216566562652588},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.560871422290802},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.5092405080795288},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48358768224716187},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44550079107284546},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08746764063835144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8423694372177124},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6216566562652588},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.560871422290802},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.5092405080795288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48358768224716187},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44550079107284546},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08746764063835144},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.acl-long.115","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.115","pdf_url":"https://aclanthology.org/2023.acl-long.115.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.acl-long.115","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.115","pdf_url":"https://aclanthology.org/2023.acl-long.115.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4331521547","display_name":"Collaborative Research: Language Documentation with an Artificial Intelligence (AI) Helper","funder_award_id":"2109578","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385572115.pdf"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1566289585","https://openalex.org/W1663984431","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2123024445","https://openalex.org/W2194775991","https://openalex.org/W2252200119","https://openalex.org/W2395611524","https://openalex.org/W2546696630","https://openalex.org/W2563399268","https://openalex.org/W2583186419","https://openalex.org/W2585654394","https://openalex.org/W2618530766","https://openalex.org/W2903343986","https://openalex.org/W2933138175","https://openalex.org/W2949303037","https://openalex.org/W2962854379","https://openalex.org/W2962862718","https://openalex.org/W2963250244","https://openalex.org/W2963331233","https://openalex.org/W2963341956","https://openalex.org/W2963532001","https://openalex.org/W2963909453","https://openalex.org/W2966715458","https://openalex.org/W2971207485","https://openalex.org/W2982573303","https://openalex.org/W2997331536","https://openalex.org/W3014611590","https://openalex.org/W3030437843","https://openalex.org/W3035032094","https://openalex.org/W3035390927","https://openalex.org/W3035448310","https://openalex.org/W3036601975","https://openalex.org/W3090449556","https://openalex.org/W3093517588","https://openalex.org/W3095410713","https://openalex.org/W3099793224","https://openalex.org/W3118578889","https://openalex.org/W3119308075","https://openalex.org/W3156892778","https://openalex.org/W3169483174","https://openalex.org/W3175746962","https://openalex.org/W3176252609","https://openalex.org/W3206010442","https://openalex.org/W3213029956","https://openalex.org/W4229024503","https://openalex.org/W4281255291","https://openalex.org/W4281684559","https://openalex.org/W4285077564","https://openalex.org/W4287330433","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4311000453","https://openalex.org/W4385245566","https://openalex.org/W4385567159"],"related_works":["https://openalex.org/W1974878518","https://openalex.org/W2600707098","https://openalex.org/W2435130738","https://openalex.org/W2610387714","https://openalex.org/W1512718085","https://openalex.org/W1484029852","https://openalex.org/W4379525811","https://openalex.org/W2167662847","https://openalex.org/W3198474835","https://openalex.org/W1569841287"],"abstract_inverted_index":{"We":[0,80,107],"present":[1],"BIG-C":[2],"(Bemba":[3],"Image":[4],"Grounded":[5],"Conversations),":[6],"a":[7,24],"large":[8],"multimodal":[9,102],"dataset":[10,42,113],"for":[11,135],"Bemba.":[12],"While":[13],"Bemba":[14,49],"is":[15,43],"the":[16,30,112,116,128,138],"most":[17],"populous":[18],"language":[19,33,36],"of":[20,26,32,45,71,104],"Zambia,":[21],"it":[22],"exhibits":[23],"dearth":[25],"resources":[27],"which":[28],"render":[29],"development":[31],"technologies":[34],"or":[35],"processing":[37],"research":[38,117,123],"almost":[39],"impossible.":[40],"The":[41],"comprised":[44],"multi-turn":[46],"dialogues":[47],"between":[48],"speakers":[50],"based":[51],"on":[52,84],"images,":[53],"transcribed":[54],"and":[55,77,91,96,124,131,145],"translated":[56],"into":[57],"English.":[58],"There":[59],"are":[60,147],"more":[61,67],"than":[62,68],"92,000":[63],"utterances/sentences,":[64],"amounting":[65],"to":[66,115],"180":[69],"hours":[70],"audio":[72],"data":[73,144],"with":[74],"corresponding":[75],"transcriptions":[76],"English":[78],"translations.":[79],"also":[81],"provide":[82],"baselines":[83],"speech":[85,92],"recognition":[86],"(ASR),":[87],"machine":[88],"translation":[89,93],"(MT)":[90],"(ST)":[94],"tasks,":[95],"sketch":[97],"out":[98],"other":[99],"potential":[100],"future":[101],"uses":[103],"our":[105],"dataset.":[106],"hope":[108],"that":[109],"by":[110],"making":[111],"available":[114],"community,":[118],"this":[119],"work":[120],"will":[121],"foster":[122],"encourage":[125],"collaboration":[126],"across":[127],"language,":[129],"speech,":[130],"vision":[132],"communities":[133],"especially":[134],"languages":[136],"outside":[137],"\u201ctraditionally\u201d":[139],"used":[140],"high-resourced":[141],"ones.":[142],"All":[143],"code":[146],"publicly":[148],"available:":[149],"[https://github.com/csikasote/bigc](https://github.com/csikasote/bigc).":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}