{"id":"https://openalex.org/W4395702991","doi":"https://doi.org/10.1145/3603287.3651197","title":"Toshakhana: A Multidimensional Panjabi Corpus in Gurmukhi Script","display_name":"Toshakhana: A Multidimensional Panjabi Corpus in Gurmukhi Script","publication_year":2024,"publication_date":"2024-04-18","ids":{"openalex":"https://openalex.org/W4395702991","doi":"https://doi.org/10.1145/3603287.3651197"},"language":"en","primary_location":{"id":"doi:10.1145/3603287.3651197","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603287.3651197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Southeast Conference on ZZZ","raw_type":"proceedings-article"},"type":"article","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":"https://openalex.org/A5011582632","display_name":"Arvinder Kang","orcid":"https://orcid.org/0009-0003-9222-8458"},"institutions":[{"id":"https://openalex.org/I368840534","display_name":"University of Mississippi","ror":"https://ror.org/02teq1165","country_code":"US","type":"education","lineage":["https://openalex.org/I368840534","https://openalex.org/I4210141039"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arvinder Kang","raw_affiliation_strings":["University of Mississippi, Oxford, Mississippi, USA"],"raw_orcid":"https://orcid.org/0009-0003-9222-8458","affiliations":[{"raw_affiliation_string":"University of Mississippi, Oxford, Mississippi, USA","institution_ids":["https://openalex.org/I368840534"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039440984","display_name":"Thai Le","orcid":"https://orcid.org/0000-0001-9632-6870"},"institutions":[{"id":"https://openalex.org/I368840534","display_name":"University of Mississippi","ror":"https://ror.org/02teq1165","country_code":"US","type":"education","lineage":["https://openalex.org/I368840534","https://openalex.org/I4210141039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thai Le","raw_affiliation_strings":["University of Mississippi, Oxford, Mississippi, USA"],"raw_orcid":"https://orcid.org/0000-0001-9632-6870","affiliations":[{"raw_affiliation_string":"University of Mississippi, Oxford, Mississippi, USA","institution_ids":["https://openalex.org/I368840534"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049759544","display_name":"Yixin Chen","orcid":"https://orcid.org/0000-0001-7645-674X"},"institutions":[{"id":"https://openalex.org/I368840534","display_name":"University of Mississippi","ror":"https://ror.org/02teq1165","country_code":"US","type":"education","lineage":["https://openalex.org/I368840534","https://openalex.org/I4210141039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yixin Chen","raw_affiliation_strings":["University of Mississippi, Oxford, Mississippi, USA"],"raw_orcid":"https://orcid.org/0000-0001-7645-674X","affiliations":[{"raw_affiliation_string":"University of Mississippi, Oxford, Mississippi, USA","institution_ids":["https://openalex.org/I368840534"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011582632"],"corresponding_institution_ids":["https://openalex.org/I368840534"],"apc_list":null,"apc_paid":null,"fwci":2.6681,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87199301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"278","last_page":"283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13122","display_name":"Linguistics and Cultural Studies","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13122","display_name":"Linguistics and Cultural Studies","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13073","display_name":"China's Ethnic Minorities and Relations","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6453922986984253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5645078420639038},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5002074241638184}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6453922986984253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5645078420639038},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5002074241638184}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3603287.3651197","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603287.3651197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM Southeast Conference on ZZZ","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W631428938","https://openalex.org/W2041197998","https://openalex.org/W2612906177","https://openalex.org/W2981698498"],"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/W3204019825"],"abstract_inverted_index":{"Panjabi":[0,41,81],"(also":[1],"referred":[2],"to":[3,10,61,77],"as":[4],"Punjabi)":[5],"is":[6,25,42,74],"a":[7,11,56],"name":[8],"given":[9],"collection":[12],"of":[13,21,37,63,67],"tonal":[14],"languages":[15],"originating":[16],"in":[17,31,44,83],"the":[18,26,32,38,79],"Punjab":[19],"area":[20],"South":[22],"Asia.":[23],"It":[24],"ninth":[27],"most":[28],"spoken":[29],"language":[30],"world":[33,39],"-":[34,47],"roughly":[35],"1.9%":[36],"population.":[40],"written":[43],"two":[45],"scripts":[46],"Gurmukhi":[48,84],"and":[49],"Shahmukhi.":[50],"Yet":[51],"it":[52],"can":[53],"be":[54],"considered":[55],"\"low":[57],"resource":[58],"language\"":[59],"due":[60],"lack":[62],"basic":[64],"building":[65],"blocks":[66],"Natural":[68],"Language":[69],"Processing":[70],"(NLP)":[71],"research.":[72],"Toshakhana":[73],"our":[75],"attempt":[76],"build":[78],"first":[80],"corpus":[82],"script":[85],"with":[86],"temporal":[87],"component.":[88]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
