{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/exploration-and-exploitation-two-ways-to","title":"Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models","arxiv_id":"2105.14813","date":"2021-05-31","proceeding":"ACL 2021 5","authors":["Chong Li","Cenyuan Zhang","Xiaoqing Zheng","Xuanjing Huang"],"abstract":"A sequence-to-sequence learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spelling errors as input and outputs the corrected one. However, CSC models may fail to correct spelling errors covered by the confusion sets, and also will encounter unseen ones. We propose a method, which continually identifies the weak spots of a model to generate more valuable training instances, and apply a task-specific pre-training strategy to enhance the model. The generated adversarial examples are gradually added to the training set. Experimental results show that such an adversarial training method combined with the pretraining strategy can improve both the generalization and robustness of multiple CSC models across three different datasets, achieving stateof-the-art performance for CSC task.","url_abs":"https://arxiv.org/abs/2105.14813v2","url_pdf":"https://arxiv.org/pdf/2105.14813v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"exploration-and-exploitation-two-ways-to","repo_url":"https://github.com/FDChongli/TwoWaysToImproveCSC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"spelling-correction","task_name":"Spelling Correction"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.14813","atlas_url":"https://app.syntology.ai/?focus=2105.14813","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}