{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T18:49:19Z","timestamp":1776106159866,"version":"3.50.1"},"reference-count":16,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T00:00:00Z","timestamp":1715299200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2024,5,31]]},"abstract":"<jats:p>Scholars in the humanities heavily rely on ancient manuscripts to study history, religion, and socio-political structures of the past. Significant efforts have been devoted to digitizing these precious manuscripts using OCR technology. However, most manuscripts have been blemished over the centuries, making it unrealistic for OCR programs to accurately capture faded characters. This work presents the Transformer + Confidence Score mechanism architecture for post-processing Google\u2019s Tibetan OCR-ed outputs. According to the Loss and Character Error Rate metrics, our Transformer + Confidence Score mechanism architecture proves superior to the Transformer, LSTM-to-LSTM, and GRU-to-GRU architectures. Our method can be adapted to any language dealing with post-processing OCR outputs.<\/jats:p>","DOI":"10.1145\/3654811","type":"journal-article","created":{"date-parts":[[2024,3,30]],"date-time":"2024-03-30T09:24:01Z","timestamp":1711790641000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts"],"prefix":"10.1145","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1854-7968","authenticated-orcid":false,"given":"Queenie","family":"Luo","sequence":"first","affiliation":[{"name":"Harvard University, Cambridge, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1723-5063","authenticated-orcid":false,"given":"Yung-Sung","family":"Chuang","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology (MIT), Cambridge, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,10]]},"reference":[{"key":"e_1_3_2_2_2","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau Dzmitry","year":"2014","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014).","journal-title":"arXiv preprint arXiv:1409.0473"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4423"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1154"},{"key":"e_1_3_2_5_2","article-title":"Byte-level grammatical error correction using synthetic and curated corpora","author":"Ing\u00f3lfsd\u00f3ttir Svanhv\u00edt Lilja","year":"2023","unstructured":"Svanhv\u00edt Lilja Ing\u00f3lfsd\u00f3ttir, P\u00e9tur Orri Ragnarsson, Haukur P\u00e1ll J\u00f3nsson, Haukur Barri S\u00edmonarson, Vilhj\u00e1lmur \u00deorsteinsson, and V\u00e9steinn Sn\u00e6bjarnarson. 2023. Byte-level grammatical error correction using synthetic and curated corpora. arXiv preprint arXiv:2305.17906 (2023).","journal-title":"arXiv preprint arXiv:2305.17906"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1002"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1055"},{"key":"e_1_3_2_8_2","article-title":"TrOCR: Transformer-based optical character recognition with pre-trained models. arXiv 2021","author":"Li Minghao","year":"2021","unstructured":"Minghao Li, Tengchao Lv, Lei Cui, Yijuan Lu, Dinei Florencio, Cha Zhang, Zhoujun Li, and Furu Wei. 2021. TrOCR: Transformer-based optical character recognition with pre-trained models. arXiv 2021. arXiv preprint arXiv:2109.10282 (2021).","journal-title":"arXiv preprint arXiv:2109.10282"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1333"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/GCON58516.2023.10183509"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_13_2","article-title":"Bangla grammatical error detection using T5 transformer model","author":"Shahgir H. A. Z.","year":"2023","unstructured":"H. A. Z. Shahgir and Khondker Salman Sayeed. 2023. Bangla grammatical error detection using T5 transformer model. arXiv preprint arXiv:2303.10612 (2023).","journal-title":"arXiv preprint arXiv:2303.10612"},{"key":"e_1_3_2_14_2","article-title":"A survey of deep learning approaches for OCR and document understanding","author":"Subramani Nishant","year":"2020","unstructured":"Nishant Subramani, Alexandre Matton, Malcolm Greaves, and Adrian Lam. 2020. A survey of deep learning approaches for OCR and document understanding. arXiv preprint arXiv:2011.13534 (2020).","journal-title":"arXiv preprint arXiv:2011.13534"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.3215"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03762"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1014"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654811","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3654811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:09Z","timestamp":1750291569000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3654811"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,10]]},"references-count":16,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5,31]]}},"alternative-id":["10.1145\/3654811"],"URL":"https:\/\/doi.org\/10.1145\/3654811","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,10]]},"assertion":[{"value":"2023-06-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-17","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}