{"id":"https://openalex.org/W7140092333","doi":"https://doi.org/10.18653/v1/2026.eacl-short.19","title":"Optical Character Recognition for the International Phonetic Alphabet","display_name":"Optical Character Recognition for the International Phonetic Alphabet","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140092333","doi":"https://doi.org/10.18653/v1/2026.eacl-short.19"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-short.19","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-short.19","pdf_url":"https://aclanthology.org/2026.eacl-short.19.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short 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.eacl-short.19.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029820736","display_name":"Shu Okabe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shu Okabe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130352392","display_name":"Dejvi Zelo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dejvi Zelo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130327655","display_name":"Alexander Fraser","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Fraser","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"265","last_page":"273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.5475999712944031,"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":0.5475999712944031,"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":0.2102999985218048,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.010599999688565731,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.44909998774528503},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.4018000066280365},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.352400004863739},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.32350000739097595},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31520000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5845999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.522599995136261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4788999855518341},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.4018000066280365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3758000135421753},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2667999863624573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-short.19","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-short.19","pdf_url":"https://aclanthology.org/2026.eacl-short.19.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-short.19","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-short.19","pdf_url":"https://aclanthology.org/2026.eacl-short.19.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140092333.pdf","grobid_xml":"https://content.openalex.org/works/W7140092333.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"grammar":[1,55],"books":[2],"are":[3],"increasingly":[4],"used":[5,39],"as":[6],"additional":[7],"reference":[8],"resources":[9],"specifically":[10],"for":[11,58,103],"very":[12],"low-resource":[13],"languages,":[14],"a":[15,36,67,83],"significant":[16],"portion":[17],"comes":[18],"from":[19],"scans":[20],"and":[21,64,66,80,82,94],"relies":[22],"on":[23,35,72],"the":[24,27,45,115],"quality":[25],"of":[26],"Optical":[28],"Character":[29],"Recognition":[30],"(OCR)":[31],"tool.We":[32],"focus":[33],"here":[34],"particular":[37],"script":[38],"in":[40,90,106],"linguistics":[41],"to":[42,109,119],"transcribe":[43],"sounds:":[44],"International":[46],"Phonetic":[47],"Alphabet":[48],"(IPA).We":[49],"consider":[50],"two":[51,59,75],"data":[52],"sources:":[53],"actual":[54],"book":[56],"PDFs":[57],"languages":[60],"under":[61],"documentation,":[62],"Japhug":[63],"Kagayanen,":[65],"synthetically":[68],"generated":[69],"dataset":[70,117],"based":[71],"Wiktionary.We":[73],"compare":[74],"neural":[76],"OCR":[77],"frameworks,":[78],"Tesseract":[79],"Calamari,":[81],"recent":[84],"large":[85],"vision-language":[86],"model,":[87],"Qwen2.5-VL-7B,all":[88],"three":[89],"an":[91],"off-theshelf":[92],"setting":[93],"with":[95,114],"fine-tuning.While":[96],"their":[97],"zero-shot":[98],"performance":[99],"is":[100],"relatively":[101],"poor":[102],"IPA":[104],"characters":[105],"general":[107],"due":[108],"character":[110],"set":[111],"mismatch,":[112],"fine-tuning":[113],"synthetic":[116],"leads":[118],"notable":[120],"improvements.":[121]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-24T00:00:00"}
