{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T12:02:40Z","timestamp":1779796960202,"version":"3.53.1"},"reference-count":0,"publisher":"Agora University of Oradea","issue":"3","license":[{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["INT J COMPUT COMMUN, Int. J. Comput. Commun. Control"],"abstract":"<jats:p>Chinese spelling correction (CSC) in legal texts faces unique challenges due to specialized terminology and complex error patterns. To address this gap, we propose Multi-granularity Curriculum Learning (mgCL), a novel two-level adaptive training framework that integrates batch-level and instance-level curricula. At the batch level, mgCL dynamically prioritizes training samples based on cross-entropy-derived difficulty, ensuring the model is exposed to increasingly complex examples in line with its evolving competence. At the instance level, mgCL leverages Monte Carlo Dropout to quantify prediction uncertainty and focus correction on challenging characters, particularly domain-specific legal terms. To facilitate evaluation in this domain, we also introduce CNLAW, a novel benchmark dataset for legal-domain CSC, featuring diverse error patterns and extensive legal terminology. Experiments present the effectiveness of our framework: on CNLAW, mgCL achieves 98.02% F1, outperforming the strong Rephrasing Language Model (ReLM) baseline (96.75%), and dramatically reduces the False Positive Rate (FPR) from 1.60% to 0.16%. Moreover, robust performance on the widely used SIGHAN15 benchmark confirms mgCL\u2019s cross-domain generalization.<\/jats:p>","DOI":"10.15837\/ijccc.2026.3.7213","type":"journal-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T11:13:25Z","timestamp":1779794005000},"source":"Crossref","is-referenced-by-count":0,"title":["Multi-granularity Curriculum Learning for Chinese Spelling Correction in Legal Texts"],"prefix":"10.15837","volume":"21","author":[{"given":"Shijin","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yabo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"6528","published-online":{"date-parts":[[2026,5,26]]},"container-title":["INTERNATIONAL JOURNAL OF COMPUTERS  COMMUNICATIONS &amp; CONTROL"],"original-title":[],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T11:13:25Z","timestamp":1779794005000},"score":1,"resource":{"primary":{"URL":"https:\/\/univagora.ro\/jour\/index.php\/ijccc\/article\/view\/7213"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":0,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,5,26]]}},"URL":"https:\/\/doi.org\/10.15837\/ijccc.2026.3.7213","relation":{},"ISSN":["1841-9844","1841-9836"],"issn-type":[{"value":"1841-9844","type":"electronic"},{"value":"1841-9836","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5,26]]}}}