{"id":"https://openalex.org/W6907372597","doi":"https://doi.org/10.21227/y8f2-nk02","title":"TamilCOCO Dataset","display_name":"TamilCOCO Dataset","publication_year":2025,"publication_date":"2025-01-09","ids":{"openalex":"https://openalex.org/W6907372597","doi":"https://doi.org/10.21227/y8f2-nk02"},"language":"en","primary_location":{"id":"doi:10.21227/y8f2-nk02","is_oa":true,"landing_page_url":"https://doi.org/10.21227/y8f2-nk02","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"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/y8f2-nk02","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"V, Jothi Prakash","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"V, Jothi Prakash","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/tamil","display_name":"Tamil","score":0.9613999724388123},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8715000152587891},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5184999704360962},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.46619999408721924},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44369998574256897},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.35499998927116394}],"concepts":[{"id":"https://openalex.org/C140688305","wikidata":"https://www.wikidata.org/wiki/Q5885","display_name":"Tamil","level":2,"score":0.9613999724388123},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8715000152587891},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6288999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6258999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6062999963760376},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4869999885559082},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C2987496018","wikidata":"https://www.wikidata.org/wiki/Q1860","display_name":"English language","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21227/y8f2-nk02","is_oa":true,"landing_page_url":"https://doi.org/10.21227/y8f2-nk02","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"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/y8f2-nk02","is_oa":true,"landing_page_url":"https://doi.org/10.21227/y8f2-nk02","pdf_url":null,"source":{"id":"https://openalex.org/S7407051695","display_name":"IEEE DataPort","issn_l":null,"issn":[],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"TamilCOCO":[0],"is":[1],"a":[2,12],"novel":[3],"bilingual":[4],"image":[5,20,52],"captioning":[6],"dataset":[7,16],"specifically":[8],"designed":[9],"for":[10,50,79,108],"Tamil,":[11,94],"low-resource":[13],"language.":[14],"This":[15],"facilitates":[17],"research":[18],"in":[19,53,91],"captioning,":[21],"cross-lingual":[22,96],"natural":[23],"language":[24],"processing,":[25],"and":[26,76,93,104],"culturally":[27,77,105],"adapted":[28,78],"AI":[29],"applications.Dataset":[30],"StatisticsTotal":[31],"Rows:&nbsp;305,340Total":[32],"Columns:&nbsp;3Unique":[33],"Images:&nbsp;63,062Unique":[34],"English":[35,66,92],"Captions:&nbsp;303,036Unique":[36],"Tamil":[37,73,99],"Captions:&nbsp;N/A":[38],"(translations":[39],"are":[40],"not":[41],"unique":[42],"due":[43],"to":[44],"possible":[45],"repetitions)Column":[46],"Descriptionsimage_id:":[47],"Unique":[48],"identifier":[49],"each":[51],"the":[54,57,62,69],"dataset.":[55],"Represents":[56],"visual":[58],"content":[59],"associated":[60],"with":[61],"captions.caption_english:":[63],"The":[64,71],"original":[65],"caption":[67],"describing":[68],"image.raw_caption_tamil:":[70],"corresponding":[72],"caption,":[74],"translated":[75],"relevance.FeaturesLanguage":[80],"Pair:":[81],"English-TamilData":[82],"Type:":[83],"Textual":[84],"descriptions":[85],"(image":[86],"captions)Multilingual":[87],"Support:":[88],"Bilingual":[89],"captions":[90,100],"enabling":[95],"applications.Cultural":[97],"Adaptation:":[98],"incorporate":[101],"idiomatic":[102],"expressions":[103],"specific":[106],"terms":[107],"enhanced":[109],"relevance.":[110]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
