{"id":"https://openalex.org/W7166825189","doi":"https://doi.org/10.18653/v1/2026.acl-long.671","title":"Digitizing Nepal\u2019s Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts","display_name":"Digitizing Nepal\u2019s Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166825189","doi":"https://doi.org/10.18653/v1/2026.acl-long.671"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.671","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.671","pdf_url":"https://aclanthology.org/2026.acl-long.671.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 64th 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/2026.acl-long.671.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139791832","display_name":"Anjali Sarawgi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anjali Sarawgi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114076222","display_name":"Esteban Garces Arias","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Esteban Garces Arias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091778335","display_name":"Christof Zotter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christof Zotter","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":210.6667,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99894459,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"14720","last_page":"14746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.27799999713897705,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.27799999713897705,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"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/T11657","display_name":"Digital and Traditional Archives Management","score":0.0544000007212162,"subfield":{"id":"https://openalex.org/subfields/1206","display_name":"Conservation"},"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/T13194","display_name":"ICT in Developing Communities","score":0.054099999368190765,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/nepali","display_name":"Nepali","score":0.7129999995231628},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6607999801635742},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.2948000133037567},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2583000063896179}],"concepts":[{"id":"https://openalex.org/C2780068402","wikidata":"https://www.wikidata.org/wiki/Q33823","display_name":"Nepali","level":2,"score":0.7129999995231628},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6607999801635742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45179998874664307},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.40369999408721924},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2567000091075897},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.24690000712871552},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2303999960422516}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.671","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.671","pdf_url":"https://aclanthology.org/2026.acl-long.671.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.671","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.671","pdf_url":"https://aclanthology.org/2026.acl-long.671.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4522666335105896,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310696","display_name":"Heidelberger Akademie der Wissenschaften","ror":"https://ror.org/02dvf9b44"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166825189.pdf","grobid_xml":"https://content.openalex.org/works/W7166825189.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,67],"first":[4],"end-to-end":[5],"pipeline":[6],"for":[7,12,88],"Handwritten":[8],"Text":[9],"Recognition":[10],"(HTR)":[11],"Old":[13],"Nepali,":[14],"a":[15,22,41],"historically":[16],"significant":[17],"but":[18],"lowresource":[19],"language.We":[20],"adopt":[21],"line-level":[23],"transcription":[24],"approach":[25],"and":[26,31,51,55,64,79],"systematically":[27],"explore":[28],"encoder-decoder":[29],"architectures":[30],"data-centric":[32],"techniques":[33],"to":[34,59,82],"improve":[35],"recognition":[36],"accuracy.Our":[37],"best":[38],"model":[39,62,77],"achieves":[40],"Character":[42],"Error":[43],"Rate":[44],"(CER)":[45],"of":[46],"4.9%.In":[47],"addition,":[48],"we":[49,72],"implement":[50],"evaluate":[52],"decoding":[53],"strategies":[54],"analyze":[56],"tokenlevel":[57],"confusions":[58],"better":[60],"understand":[61],"behavior":[63],"error":[65],"patterns.Although":[66],"evaluation":[68,80],"dataset":[69],"is":[70],"confidential,":[71],"release":[73],"our":[74],"training":[75],"code,":[76],"configurations,":[78],"scripts":[81],"support":[83],"further":[84],"research":[85],"on":[86],"HTR":[87],"low-resource":[89],"historical":[90],"scripts.":[91]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
