{"id":"https://openalex.org/W4393342143","doi":"https://doi.org/10.1145/3654811","title":"Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts","display_name":"Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts","publication_year":2024,"publication_date":"2024-03-30","ids":{"openalex":"https://openalex.org/W4393342143","doi":"https://doi.org/10.1145/3654811"},"language":"en","primary_location":{"id":"doi:10.1145/3654811","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3654811","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3654811","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3654811","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051028201","display_name":"Queenie Luo","orcid":"https://orcid.org/0009-0004-1854-7968"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Queenie Luo","raw_affiliation_strings":["Harvard University, Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058729228","display_name":"Yung-Sung Chuang","orcid":"https://orcid.org/0000-0002-1723-5063"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yung-Sung Chuang","raw_affiliation_strings":["Massachusetts Institute of Technology (MIT), Cambridge, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology (MIT), Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051028201"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":0.5263,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.617872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"23","issue":"5","first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/spelling","display_name":"Spelling","score":0.9423795938491821},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.489434152841568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4565122127532959},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42379799485206604},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3280680179595947},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32211416959762573},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.056296080350875854}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.9423795938491821},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.489434152841568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4565122127532959},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42379799485206604},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3280680179595947},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32211416959762573},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.056296080350875854}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3654811","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3654811","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3654811","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3654811","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3654811","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3654811","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393342143.pdf","grobid_xml":"https://content.openalex.org/works/W4393342143.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2606974598","https://openalex.org/W2936597270","https://openalex.org/W2962784628","https://openalex.org/W2963655793","https://openalex.org/W2963881719","https://openalex.org/W2964082031","https://openalex.org/W2964165364","https://openalex.org/W2970076840","https://openalex.org/W3109569233","https://openalex.org/W4297734170","https://openalex.org/W4330339460","https://openalex.org/W4378770788","https://openalex.org/W4385079034","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2161008081","https://openalex.org/W2100947578","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2081317458","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Scholars":[0],"in":[1],"the":[2,17,39,55,70,87],"humanities":[3],"heavily":[4],"rely":[5],"on":[6],"ancient":[7],"manuscripts":[8,28,34],"to":[9,24,47,69,86,98],"study":[10],"history,":[11],"religion,":[12],"and":[13,72,90],"socio-political":[14],"structures":[15],"of":[16],"past.":[18],"Significant":[19],"efforts":[20],"have":[21,35],"been":[22,36],"devoted":[23],"digitizing":[25],"these":[26],"precious":[27],"using":[29],"OCR":[30,45,104],"technology.":[31],"However,":[32],"most":[33],"blemished":[37],"over":[38],"centuries,":[40],"making":[41],"it":[42],"unrealistic":[43],"for":[44,62],"programs":[46],"accurately":[48],"capture":[49],"faded":[50],"characters.":[51],"This":[52],"work":[53],"presents":[54],"Transformer":[56,78],"+":[57,79],"Confidence":[58,80],"Score":[59,81],"mechanism":[60,82],"architecture":[61,83],"post-processing":[63,103],"Google\u2019s":[64],"Tibetan":[65],"OCR-ed":[66],"outputs.":[67,105],"According":[68],"Loss":[71],"Character":[73],"Error":[74],"Rate":[75],"metrics,":[76],"our":[77],"proves":[84],"superior":[85],"Transformer,":[88],"LSTM-to-LSTM,":[89],"GRU-to-GRU":[91],"architectures.":[92],"Our":[93],"method":[94],"can":[95],"be":[96],"adapted":[97],"any":[99],"language":[100],"dealing":[101],"with":[102]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
