{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:35:11Z","timestamp":1763202911768,"version":"3.41.0"},"reference-count":42,"publisher":"Association for Computing Machinery (ACM)","issue":"11","license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62476127, 62106105"],"award-info":[{"award-number":["62476127, 62106105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Scientific Research Starting Foundation of Nanjing University of Aeronautics and Astronautics","award":["YQR21022"],"award-info":[{"award-number":["YQR21022"]}]},{"name":"High Performance Computing Platform of Nanjing University of Aeronautics and Astronautics"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2024,11,30]]},"abstract":"<jats:p>\n            Chinese Spelling Check (CSC) is a meaningful task in the area of natural language processing, which aims at detecting spelling errors in Chinese texts and then correcting these errors. Current typical CSC models have shown impressive performance in general datasets with the help of pretrained language models such as BERT, but they suffer great performance loss in downstream tasks with domain-specific terms because they are primarily trained on general corpora. To verify the cross-domain adaptation ability of these models, we build three new datasets with abundant domain-specific terms on financial, medical, and legal domains and conduct empirical investigations on them in the corresponding domain-specific test datasets to verify the cross-domain adaptation ability. In response to the poor performance of the existing models, we propose a framework named\n            <jats:italic>uChecker,<\/jats:italic>\n            which utilizes an unsupervised method in spelling error detection and correction. Experimental results prove that uChecker can perform well in domain-specific test datasets while not losing its performance in the general domain.\n          <\/jats:p>","DOI":"10.1145\/3689821","type":"journal-article","created":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T11:24:37Z","timestamp":1724757877000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["An Unsupervised Domain-Adaptive Framework for Chinese Spelling Checking"],"prefix":"10.1145","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5217-6704","authenticated-orcid":false,"given":"Xi","family":"Wang","sequence":"first","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3419-7760","authenticated-orcid":false,"given":"Ruoqing","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8044-2284","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1474-3692","authenticated-orcid":false,"given":"Piji","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"962","volume-title":"Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC \u201916)","author":"Afli Haithem","year":"2016","unstructured":"Haithem Afli, Zhengwei Qiu, Andy Way, and P\u00e1raic Sheridan. 2016. Using SMT for OCR error correction of historical texts. In Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC \u201916). 962\u2013966. https:\/\/aclanthology.org\/L16-1153"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Zuyi Bao Chen Li and Rui Wang. 2020. Chunk-based Chinese spelling check with global optimization. In Findings of the Association for Computational Linguistics: EMNLP 2020 Trevor Cohn Yulan He and Yang Liu (Eds.). Association for Computational Linguistics 2031\u20132040. 10.18653\/v1\/2020.findings-emnlp.184","DOI":"10.18653\/v1\/2020.findings-emnlp.184"},{"key":"e_1_3_2_4_2","first-page":"79","volume-title":"Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing","author":"Chen Kuan-Yu","year":"2013","unstructured":"Kuan-Yu Chen, Hung-Shin Lee, Chung-Han Lee, Hsin-Min Wang, and Hsin-Hsi Chen. 2013. A study of language modeling for Chinese spelling check. In Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing. 79\u201383. https:\/\/aclanthology.org\/W13-4414"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.81"},{"key":"e_1_3_2_6_2","first-page":"49","volume-title":"Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing","author":"Chiu Hsun-Wen","year":"2013","unstructured":"Hsun-Wen Chiu, Jian-Cheng Wu, and Jason S. Chang. 2013. Chinese spelling checker based on statistical machine translation. In Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing. 49\u201353. https:\/\/aclanthology.org\/W13-4408"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_8_2","first-page":"194","volume-title":"Proceedings of the 26th International Conference on Computational Linguistics: System Demonstrations","author":"Dong Shichao","year":"2016","unstructured":"Shichao Dong, Gabriel Pui Cheong Fung, Binyang Li, Baolin Peng, Ming Liao, Jia Zhu, and Kam-Fai Wong. 2016. ACE: Automatic colloquialism, typographical and orthographic errors detection for Chinese language. In Proceedings of the 26th International Conference on Computational Linguistics: System Demonstrations(COLING \u201916). 194\u2013197. https:\/\/aclanthology.org\/C16-2041"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.5555\/1873781.1873822"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Zhao Guo Yuan Ni Keqiang Wang Wei Zhu and Guotong Xie. 2021. Global attention decoder for Chinese spelling error correction. In Findings of the Association for Computational Linguistics: ACL\/IJCNLP 2021 Chengqing Zong Fei Xia Wenjie Li and Roberto Navigli (Eds.). Association for Computational Linguistics 1410\u20131428. 10.18653\/v1\/2021.findings-acl.122","DOI":"10.18653\/v1\/2021.findings-acl.122"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5522"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.464"},{"key":"e_1_3_2_14_2","first-page":"88","volume-title":"Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing","author":"Jia Zhongye","year":"2013","unstructured":"Zhongye Jia, Peilu Wang, and Hai Zhao. 2013. Graph model for Chinese spell checking. In Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing. 88\u201392. https:\/\/aclanthology.org\/W13-4416"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/1967293.1967297"},{"key":"e_1_3_2_16_2","first-page":"739","volume-title":"COLING 2010: Posters","author":"Liu Chao-Lin","year":"2010","unstructured":"Chao-Lin Liu, Min-Hua Lai, Yi-Hsuan Chuang, and Chia-Ying Lee. 2010. Visually and phonologically similar characters in incorrect simplified Chinese words. In COLING 2010: Posters. Coling 2010 Organizing Committee, Beijing, China, 739\u2013747. https:\/\/aclanthology.org\/C10-2085"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.237"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.233"},{"key":"e_1_3_2_19_2","volume-title":"Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing (SIGHAN@IJCNLP \u201913)","author":"Liu Xiaodong","year":"2013","unstructured":"Xiaodong Liu, Fei Cheng, Yanyan Luo, Kevin Duh, and Yuji Matsumoto. 2013. A hybrid Chinese spelling correction using language model and statistical machine translation with reranking. In Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing (SIGHAN@IJCNLP \u201913). 54\u201358."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3564271"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.01815"},{"key":"e_1_3_2_23_2","article-title":"Hierarchical LSTM with adjusted temporal attention for video captioning","author":"Song Jingkuan","year":"2017","unstructured":"Jingkuan Song, Zhao Guo, Lianli Gao, Wu Liu, Dongxiang Zhang, and Heng Tao Shen. 2017. Hierarchical LSTM with adjusted temporal attention for video captioning. arXiv preprint arXiv:1706.01231 (2017).","journal-title":"arXiv preprint arXiv:1706.01231"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3106"},{"key":"e_1_3_2_25_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017), 1\u201311.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Baoxin Wang Wanxiang Che Dayong Wu Shijin Wang Guoping Hu and Ting Liu. 2021. Dynamic connected networks for Chinese spelling check. In Findings of the Association for Computational Linguistics: ACL\/IJCNLP 2021 Chenqing Zong Fei Xia Wenjie Li and Roberto Navigli (Eds.). Association for Computational Linguistics 2437\u20132446. 10.18653\/v1\/2021.findings-acl.216","DOI":"10.18653\/v1\/2021.findings-acl.216"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1273"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1273"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1578"},{"key":"e_1_3_2_30_2","volume-title":"Proceedings of the CIPS-SIGHAN Joint Conference on Chinese Language Processing","author":"Wu Shih-Hung","year":"2010","unstructured":"Shih-Hung Wu, Yong-Zhi Chen, Ping-Che Yang, Tsun Ku, and Chao-Lin Liu. 2010. Reducing the false alarm rate of Chinese character error detection and correction. In Proceedings of the CIPS-SIGHAN Joint Conference on Chinese Language Processing. https:\/\/aclanthology.org\/W10-4107"},{"key":"e_1_3_2_31_2","first-page":"35","volume-title":"Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing","author":"Wu Shih-Hung","year":"2013","unstructured":"Shih-Hung Wu, Chao-Lin Liu, and Lung-Hao Lee. 2013. Chinese spelling check evaluation at SIGHAN Bake-off 2013. In Proceedings of the 7th SIGHAN Workshop on Chinese Language Processing. 35\u201342. https:\/\/aclanthology.org\/W13-4406"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","unstructured":"Chaojun Xiao Haoxi Zhong Zhipeng Guo Cunchao Tu Zhiyuan Liu Maosong Sun Yansong Feng Xianpei Han Zhen Hu Heng Wang and Jianfeng Xu. 2018. CAIL2018: A large-scale legal dataset for judgment prediction. arXiv:1807.02478 (2018). 10.48550\/ARXIV.1807.02478","DOI":"10.48550\/ARXIV.1807.02478"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3120"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-6825"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.64"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-6835"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-6820"},{"key":"e_1_3_2_38_2","volume-title":"Building a Pediatric Medical Corpus: Word Segmentation and Named Entity Annotation","author":"Zan H.","year":"2021","unstructured":"H. Zan, W. Li, K. Zhang, Y. Ye, and Z. Sui. 2021. Building a Pediatric Medical Corpus: Word Segmentation and Named Entity Annotation. Chinese Lexical Semantics."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.544"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.198"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.82"},{"key":"e_1_3_2_42_2","article-title":"Spelling error correction with soft-masked BERT","volume":"2005","author":"Zhang Shaohua","year":"2020","unstructured":"Shaohua Zhang, Haoran Huang, Jicong Liu, and Hang Li. 2020. Spelling error correction with soft-masked BERT. CoRR abs\/2005.07421 (2020). https:\/\/arxiv.org\/abs\/2005.07421","journal-title":"CoRR"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Haoxi Zhong Chaojun Xiao Zhipeng Guo Cunchao Tu Zhiyuan Liu Maosong Sun Yansong Feng Xianpei Han Zhen Hu Heng Wang and Jianfeng Xu. 2018. Overview of CAIL2018: Legal Judgment Prediction competition. arXiv:1810.05851 (2018). 10.48550\/ARXIV.1810.05851","DOI":"10.48550\/ARXIV.1810.05851"}],"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\/3689821","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:11Z","timestamp":1750291571000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689821"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"references-count":42,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11,30]]}},"alternative-id":["10.1145\/3689821"],"URL":"https:\/\/doi.org\/10.1145\/3689821","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"type":"print","value":"2375-4699"},{"type":"electronic","value":"2375-4702"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"2023-08-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}