{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T02:01:15Z","timestamp":1781316075967,"version":"3.54.1"},"reference-count":80,"publisher":"China Science Publishing & Media Ltd.","issue":"2","content-domain":{"domain":["engine.scichina.com"],"crossmark-restriction":false},"short-container-title":["DI"],"published-print":{"date-parts":[[2026,6,1]]},"DOI":"10.3724\/2096-7004.di.2025.0110","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T07:05:57Z","timestamp":1758524757000},"page":"20250110","update-policy":"https:\/\/doi.org\/10.1360\/scp-crossmark-policy-page","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Grammar Error Correction with Continual Knowledge Distillation and Reinforcement Learning"],"prefix":"10.3724","volume":"8","author":[{"given":"Zeming","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shihu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2026","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"null","unstructured":"J. Ye, Y. Li, Q. Zhou, Y. Li, S. Ma, H.-T. Zheng, and Y. Shen, \u201cCleme: debiasing multi-reference evaluation for grammatical error correction,\u201d arXiv preprint arXiv:2305.10819, 2023."},{"key":"null","unstructured":"Y. Li, H. Huang, S. Ma, Y. Jiang, Y. Li, F. Zhou, H.-T. Zheng, and Q. Zhou, \u201cOn the (in) effectiveness of large language models for chinese text correction,\u201d arXiv preprint arXiv:2307.09007, 2023."},{"key":"null","unstructured":"J. Ye, Y. Li, and H. Zheng, \u201cSystem report for CCL23-eval task 7: THU KELab (sz)-exploring data augmentation and denoising for Chinese grammatical error correction,\u201d in Proceedings of the 22 nd  Chinese National Conference on Computational Linguistics (Volume 3: Evaluations), M. Sun, B. Qin, X. Qiu, J. Jiang, and X. Han, Eds. Harbin, China: Chinese Information Processing Society of China, Aug. 2023, pp. 262\u2013270. [Online]. Available: https:\/\/aclanthology.org\/2023.ccl-3.29\/."},{"key":"null","unstructured":"S. Ma, Y. Li, H. Huang, S. Huang, Y. Li, H.-T. Zheng, and Y. Shen, \u201cProgressive multi-task learning framework for chinese text error correction,\u201d arXiv e-prints, pp. arXiv-2306, 2023."},{"key":"null","unstructured":"C. Bryant, Z. Yuan, M. R. Qorib, H. Cao, H. T. Ng, and T. Briscoe, \u201cGrammatical error correction: A survey of the state of the art,\u201d Computational Linguistics, vol. 49, no. 3, pp. 643\u2013701, 2023."},{"key":"null","unstructured":"C. Dong, Y. Li, H. Gong, M. Chen, J. Li, Y. Shen, and M. Yang, \u201cA survey of natural language generation,\u201d ACM Computing Surveys, vol. 55, no. 8, pp. 1\u201338, 2022."},{"key":"null","unstructured":"K. Omelianchuk, V. Atrasevych, A. Chernodub, and O. Skurzhanskyi, \u201cGector-grammatical error correction: tag, not rewrite,\u201d arXiv preprint arXiv:2005.12592, 2020."},{"key":"null","unstructured":"J. Ye, Y. Li, S. Ma, R. Xie, W. Wu, and H.-T. Zheng, \u201cFocus is what you need for chinese grammatical error correction,\u201d arXiv preprint arXiv:2210.12692, 2022."},{"key":"null","unstructured":"Y. Li, Q. Zhou, Y. Li, Z. Li, R. Liu, R. Sun, Z. Wang, C. Li, Y. Cao, and H.-T. Zheng, \u201cThe past mistake is the future wisdom: Error-driven contrastive probability optimization for chinese spell checking,\u201d arXiv preprint arXiv:2203.00991, 2022."},{"key":"null","unstructured":"D. Zhang, Y. Li, Q. Zhou, S. Ma, Y. Li, Y. Cao, and H.-T. Zheng, \u201cContextual similarity is more valuable than character similarity: An empirical study for chinese spell checking,\u201d in ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023, pp. 1\u20135."},{"key":"null","unstructured":"R.Weng, H. Yu, S. Huang, S. Cheng, and W. Luo, \u201cAcquiring knowledge from pre-trained model to neural machine translation,\u201d in Proceedings of the AAAI conference on artificial intelligence, vol. 34, no. 05, 2020, pp. 9266\u20139273."},{"key":"null","unstructured":"G. Hinton, O. Vinyals, and J. Dean, \u201cDistilling the knowledge in a neural network,\u201d arXiv preprint arXiv:1503.02531, 2015."},{"key":"null","unstructured":"J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A. A. Rusu, K. Milan, J. Quan, T. Ramalho, A. Grabska-Barwinska et al., \u201cOvercoming catastrophic forgetting in neural networks,\u201d Proceedings of the national academy of sciences, vol. 114, no. 13, pp. 3521\u20133526, 2017."},{"key":"null","unstructured":"H. T. Ng, S. M. Wu, T. Briscoe, C. Hadiwinoto, R. H. Susanto, and C. Bryant, \u201cThe conll-2014\u00a0shared task on grammatical error correction,\u201d in Proceedings of the eighteenth conference on computational natural language learning: shared task, 2014, pp. 1\u201314."},{"key":"null","unstructured":"C. Bryant, M. Felice, \u00d8. E. Andersen, and T. Briscoe, \u201cThe BEA-2019\u00a0shared task on grammatical error correction,\u201d in Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, H. Yannakoudakis, E. Kochmar, C. Leacock, N. Madnani, I. Pil\u00e1n, and T. Zesch, Eds. Florence, Italy: Association for Computational Linguistics, Aug. 2019, pp. 52\u201375. [Online]. Available: https:\/\/aclanthology.org\/W19-4406\/."},{"key":"null","unstructured":"C. Napoles, K. Sakaguchi, and J. Tetreault, \u201cJfleg: A fluency corpus and benchmark for grammatical error correction,\u201d arXiv preprint arXiv:1702.04066, 2017."},{"key":"null","unstructured":"S. Katsumata and M. Komachi, \u201cStronger baselines for grammatical error correction using a pretrained encoder-decoder model,\u201d in Proceedings of the 1 st  Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10 th  International Joint Conference on Natural Language Processing, K.-F. Wong, K. Knight, and H. Wu, Eds. Suzhou, China: Association for Computational Linguistics, Dec. 2020, pp. 827\u2013832. [Online]. Available: https:\/\/aclanthology.org\/2020.aacl-main.83\/."},{"key":"null","unstructured":"H. T. Ng, S. M. Wu, Y. Wu, C. Hadiwinoto, and J. Tetreault, \u201cThe CoNLL-2013\u00a0shared task on grammatical error correction,\u201d in Proceedings of the Seventeenth Conference on Computational Natural Language Learning: Shared Task. Sofia, Bulgaria: Association for Computational Linguistics, Aug. 2013, pp. 1\u201312. [Online]. Available: https:\/\/aclanthology.org\/W13-3601\/."},{"key":"null","unstructured":"R. Sennrich, B. Haddow, and A. Birch, \u201cImproving neural machine translation models with monolingual data,\u201d in Proceedings of the 54 th  annual meeting of the association for computational linguistics (volume 1: long papers), 2016, pp. 86\u201396."},{"key":"null","unstructured":"S. Kasewa, P. Stenetorp, and S. Riedel, \u201cWronging a right: Generating better errors to improve grammatical error detection,\u201d arXiv preprint arXiv:1810.00668, 2018."},{"key":"null","unstructured":"Z. Xie, G. Genthial, S. Xie, A. Ng, and D. Jurafsky, \u201cNoising and denoising natural language: Diverse backtranslation for grammar correction,\u201d in Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), M. Walker, H. Ji, and A. Stent, Eds. New Orleans, Louisiana: Association for Computational Linguistics, Jun. 2018, pp. 619\u2013628. [Online]. Available: https:\/\/aclanthology.org\/N18-1057\/."},{"key":"null","unstructured":"S. Kiyono, J. Suzuki, M. Mita, T. Mizumoto, and K. Inui, \u201cAn empirical study of incorporating pseudo data into grammatical error correction,\u201d arXiv preprint arXiv:1909.00502, 2019."},{"key":"null","unstructured":"J. Lichtarge, C. Alberti, S. Kumar, N. Shazeer, N. Parmar, and S. Tong, \u201cCorpora generation for grammatical error correction,\u201d arXiv preprint arXiv:1904.05780, 2019."},{"key":"null","unstructured":"W. Zhao, L. Wang, K. Shen, R. Jia, and J. Liu, \u201cImproving grammatical error correction via pre-training a copyaugmented architecture with unlabeled data,\u201d arXiv preprint arXiv:1903.00138, 2019."},{"key":"null","unstructured":"F. Stahlberg and S. Kumar, \u201cSynthetic data generation for grammatical error correction with tagged corruption models,\u201d arXiv preprint arXiv:2105.13318, 2021."},{"key":"null","unstructured":"Y. J. Choe, J. Ham, K. Park, and Y. Yoon, \u201cA neural grammatical error correction system built on better pre-training and sequential transfer learning,\u201d arXiv preprint arXiv:1907.01256, 2019."},{"key":"null","unstructured":"M. Kaneko, M. Mita, S. Kiyono, J. Suzuki, and K. Inui, \u201cEncoder-decoder models can benefit from pre-trained masked language models in grammatical error correction,\u201d arXiv preprint arXiv:2005.00987, 2020."},{"key":"null","unstructured":"S. Rothe, J. Mallinson, E. Malmi, S. Krause, and A. Severyn, \u201cA simple recipe for multilingual grammatical error correction,\u201d arXiv preprint arXiv:2106.03830, 2021."},{"key":"null","unstructured":"F. Stahlberg and S. Kumar, \u201cSynthetic data generation for low-resource grammatical error correction with tagged corruption models,\u201d in Proceedings of the 19 th  Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024), E. Kochmar, M. Bexte, J. Burstein, A. Horbach, R. Laarmann-Quante, A. Tack, V. Yaneva, and Z. Yuan, Eds. Mexico City, Mexico: Association for Computational Linguistics, Jun. 2024, pp. 11\u201316. [Online]. Available: https:\/\/aclanthology.org\/2024.bea-1.2\/."},{"key":"null","unstructured":"J. Liang, H. Yang, S. Gao, and X. Quan, \u201cEdit-wise preference optimization for grammatical error correction,\u201d in Proceedings of the 31 st  International Conference on Computational Linguistics, O. Rambow, L. Wanner, M. Apidianaki, H. Al-Khalifa, B. D. Eugenio, and S. Schockaert, Eds. Abu Dhabi, UAE: Association for Computational Linguistics, Jan. 2025, pp. 3401\u20133414. [Online]. Available: https: \/\/aclanthology.org\/2025.coling-main.229\/."},{"key":"null","unstructured":"K. Omelianchuk, A. Liubonko, O. Skurzhanskyi, A. Chernodub, O. Korniienko, and I. Samokhin, \u201cPillars of grammatical error correction: Comprehensive inspection of contemporary approaches in the era of large language models,\u201d arXiv preprint arXiv:2404.14914, 2024."},{"key":"null","unstructured":"H. Cao, L. Yuan, Y. Zhang, and H. T. Ng, \u201cUnsupervised grammatical error correction rivaling supervised methods,\u201d in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, H. Bouamor, J. Pino, and K. Bali, Eds. Singapore: Association for Computational Linguistics, Dec. 2023, pp. 3072\u20133088. [Online]. Available: https:\/\/aclanthology.org\/2023.emnlp-main.185\/."},{"key":"null","unstructured":"M. Loem, M. Kaneko, S. Takase, and N. Okazaki, \u201cExploring effectiveness of gpt-3 in grammatical error correction: A study on performance and controllability in prompt-based methods,\u201d arXiv preprint arXiv:2305.18156, 2023."},{"key":"null","unstructured":"T. Fang, S. Yang, K. Lan, D. F. Wong, J. Hu, L. S. Chao, and Y. Zhang, \u201cIs chatgpt a highly fluent grammatical error correction system? a comprehensive evaluation,\u201d arXiv preprint arXiv:2304.01746, 2023."},{"key":"null","unstructured":"J. Gou, B. Yu, S. J. Maybank, and D. Tao, \u201cKnowledge distillation: A survey,\u201d International journal of computer vision, vol. 129, no. 6, pp. 1789\u20131819, 2021."},{"key":"null","unstructured":"Y. Qin, Y. Lin, J. Yi, J. Zhang, X. Han, Z. Zhang, Y. Su, Z. Liu, P. Li, M. Sun, and J. Zhou, \u201cKnowledge inheritance for pre-trained language models,\u201d in Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Seattle, United States: Association for Computational Linguistics, Jul. 2022, pp. 3921\u20133937. [Online]. Available: https:\/\/aclanthology.org\/2022.naacl-main.288\/."},{"key":"null","unstructured":"S. I. Mirzadeh, M. Farajtabar, A. Li, N. Levine, A. Matsukawa, and H. Ghasemzadeh, \u201cImproved knowledge distillation via teacher assistant,\u201d in Proceedings of the AAAI conference on artificial intelligence, vol. 34, no. 04, 2020, pp. 5191\u20135198."},{"key":"null","unstructured":"M. Freitag, Y. Al-Onaizan, and B. Sankaran, \u201cEnsemble distillation for neural machine translation,\u201d arXiv preprint arXiv:1702.01802, 2017."},{"key":"null","unstructured":"T. Wolf, L. Debut, V. Sanh, J. Chaumond, C. Delangue, A. Moi, P. Cistac, T. Rault, R. Louf, M. Funtowicz, J. Davison, S. Shleifer, P. von Platen, C. Ma, Y. Jernite, J. Plu, C. Xu, T. Le Scao, S. Gugger, M. Drame, Q. Lhoest, and A. Rush, \u201cTransformers: State-of-the-art natural language processing,\u201d in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Q. Liu and D. Schlangen, Eds. Online: Association for Computational Linguistics, Oct. 2020, pp. 38\u201345. [Online]. Available: https:\/\/aclanthology.org\/2020.emnlp-demos.6\/."},{"key":"null","unstructured":"Y.-S. Chuang, S.-Y. Su, and Y.-N. Chen, \u201cLifelong language knowledge distillation,\u201d in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), B. Webber, T. Cohn, Y. He, and Y. Liu, Eds. Online: Association for Computational Linguistics, Nov. 2020, pp. 2914\u20132924. [Online]. Available: https:\/\/aclanthology.org\/2020.emnlp-main.233\/."},{"key":"null","unstructured":"F. Wang, J. Yan, F. Meng, and J. Zhou, \u201cSelective knowledge distillation for neural machine translation,\u201d arXiv preprint arXiv:2105.12967, 2021."},{"key":"null","unstructured":"F. Zenke, B. Poole, and S. Ganguli, \u201cContinual learning through synaptic intelligence,\u201d in Proceedings of the 34 th  International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, D. Precup and Y. W. Teh, Eds., vol. 70. PMLR, 06\u201311\u00a0Aug 2017, pp. 3987\u20133995. [Online]. Available: https:\/\/proceedings.mlr.press\/v70\/zenke17a.html."},{"key":"null","unstructured":"Y. Cao, H.-R. Wei, B. Chen, and X. Wan, \u201cContinual learning for neural machine translation,\u201d in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, K. Toutanova, A. Rumshisky, L. Zettlemoyer, D. Hakkani-Tur, I. Beltagy, S. Bethard, R. Cotterell, T. Chakraborty, and Y. Zhou, Eds. Online: Association for Computational Linguistics, Jun. 2021, pp. 3964\u20133974. [Online]. Available: https:\/\/aclanthology.org\/2021.naacl-main.310\/."},{"key":"null","unstructured":"K. Huang, P. Li, J. Ma, and Y. Liu, \u201cEntropy-based vocabulary substitution for incremental learning in multilingual neural machine translation,\u201d in Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Y. Goldberg, Z. Kozareva, and Y. Zhang, Eds. Abu Dhabi, United Arab Emirates: Association for Computational Linguistics, Dec. 2022, pp. 10537\u201310550. [Online]. Available: https:\/\/aclanthology.org\/2022.emnlp-main.720\/."},{"key":"null","unstructured":"K. Hashimoto and Y. Tsuruoka, \u201cAccelerated reinforcement learning for sentence generation by vocabulary prediction,\u201d in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), J. Burstein, C. Doran, and T. Solorio, Eds. Minneapolis, Minnesota: Association for Computational Linguistics, Jun. 2019, pp. 3115\u20133125. [Online]. Available: https:\/\/aclanthology.org\/N19-1315\/."},{"key":"null","unstructured":"G. Yasui, Y. Tsuruoka, and M. Nagata, \u201cUsing semantic similarity as reward for reinforcement learning in sentence generation,\u201d in Proceedings of the 57 th  Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, F. Alva-Manchego, E. Choi, and D. Khashabi, Eds. Florence, Italy: Association for Computational Linguistics, Jul. 2019, pp. 400\u2013406. [Online]. Available: https:\/\/aclanthology.org\/P19-2056\/."},{"key":"null","unstructured":"R. J. Williams, \u201cSimple statistical gradient-following algorithms for connectionist reinforcement learning,\u201d Machine learning, vol. 8, no. 3, pp. 229\u2013256, 1992."},{"key":"null","unstructured":"L. Weaver and N. Tao, \u201cThe optimal reward baseline for gradient-based reinforcement learning,\u201d arXiv preprint arXiv:1301.2315, 2013."},{"key":"null","unstructured":"M. Ranzato, S. Chopra, M. Auli, and W. Zaremba, \u201cSequence level training with recurrent neural networks,\u201d arXiv preprint arXiv:1511.06732, 2015."},{"key":"null","unstructured":"L. Choshen, L. Fox, Z. Aizenbud, and O. Abend, \u201cOn the weaknesses of reinforcement learning for neural machine translation,\u201d arXiv preprint arXiv:1907.01752, 2019."},{"key":"null","unstructured":"D. Silver, G. Lever, N. Heess, T. Degris, D. Wierstra, and M. Riedmiller, \u201cDeterministic policy gradient algorithms,\u201d in International conference on machine learning. Pmlr, 2014, pp. 387\u2013395."},{"key":"null","unstructured":"D. Bahdanau, P. Brakel, K. Xu, A. Goyal, R. Lowe, J. Pineau, A. Courville, and Y. Bengio, \u201cAn actor-critic algorithm for sequence prediction,\u201d arXiv preprint arXiv:1607.07086, 2016."},{"key":"null","unstructured":"P. Henderson, R. Islam, P. Bachman, J. Pineau, D. Precup, and D. Meger, \u201cDeep reinforcement learning that matters,\u201d in Proceedings of the AAAI conference on artificial intelligence, vol. 32, no. 1, 2018."},{"key":"null","unstructured":"V. Konda and J. Tsitsiklis, \u201cActor-critic algorithms,\u201d Advances in neural information processing systems, vol. 12, 1999."},{"key":"null","unstructured":"R. S. Sutton, A. G. Barto et al.,Reinforcement learning: An introduction. MIT press Cambridge, 1998, vol. 1, no. 1."},{"key":"null","unstructured":"R. S. Sutton, D. McAllester, S. Singh, and Y. Mansour, \u201cPolicy gradient methods for reinforcement learning with function approximation,\u201d Advances in neural information processing systems, vol. 12, 1999."},{"key":"null","unstructured":"J. N\u00e1plava and M. Straka, \u201cGrammatical error correction in low-resource scenarios,\u201d arXiv preprint arXiv:1910.00353, 2019."},{"key":"null","unstructured":"Y. Zhao, N. Jiang, W. Sun, and X. Wan, \u201cOverview of the nlpcc 2018\u00a0shared task: Grammatical error correction,\u201d in CCF International Conference on Natural Language Processing and Chinese Computing. Springer, 2018, pp. 439\u2013445."},{"key":"null","unstructured":"Y. Zhang, Z. Li, Z. Bao, J. Li, B. Zhang, C. Li, F. Huang, and M. Zhang, \u201cMucgec: a multi-reference multi-source evaluation dataset for chinese grammatical error correction,\u201d arXiv preprint arXiv:2204.10994, 2022."},{"key":"null","unstructured":"D. Dahlmeier and H. T. Ng, \u201cBetter evaluation for grammatical error correction,\u201d in Proceedings of the 2012 conference of the north american chapter of the association for computational linguistics: human language technologies, 2012, pp. 568\u2013572."},{"key":"null","unstructured":"C. Napoles, K. Sakaguchi, M. Post, and J. Tetreault, \u201cGround truth for grammatical error correction metrics,\u201d in Proceedings of the 53 rd  Annual Meeting of the Association for Computational Linguistics and the 7 th  International Joint Conference on Natural Language Processing (Volume 2: Short Papers), 2015, pp. 588\u2013593."},{"key":"null","unstructured":"H. Wang, M. Kurosawa, S. Katsumata, and M. Komachi, \u201cChinese grammatical correction using bert-based pretrained model,\u201d arXiv preprint arXiv:2011.02093, 2020."},{"key":"null","unstructured":"K. Fu, J. Huang, and Y. Duan, \u201cYoudao\u2019s winning solution to the nlpcc-2018 task 2 challenge: a neural machine translation approach to chinese grammatical error correction,\u201d in CCF International Conference on Natural Language Processing and Chinese Computing. Springer, 2018, pp. 341\u2013350."},{"key":"null","unstructured":"H. Ren, L. Yang, and E. Xun, \u201cA sequence to sequence learning for chinese grammatical error correction,\u201d in CCF International Conference on Natural Language Processing and Chinese Computing. Springer, 2018, pp. 401\u2013410."},{"key":"null","unstructured":"K. Yakovlev, A. Podolskiy, A. Bout, S. Nikolenko, and I. Piontkovskaya, \u201cGec-depend: Non-autoregressive grammatical error correction with decoupled permutation and decoding,\u201d arXiv preprint arXiv:2311.08191, 2023."},{"key":"null","unstructured":"H. Cao, Z. Cao, C. Hu, B. Hou, T. Xiao, and J. Zhu, \u201cImproving autoregressive grammatical error correction with non-autoregressive models,\u201d in Findings of the Association for Computational Linguistics: ACL 2023, A. Rogers, J. Boyd-Graber, and N. Okazaki, Eds. Toronto, Canada: Association for Computational Linguistics, Jul. 2023, pp. 12014\u201312027. [Online]. Available: https:\/\/aclanthology.org\/2023.findings-acl.760\/."},{"key":"null","unstructured":"J. Deng, C. Chen, C. Hou, and X. Yuan, \u201cInstructGEC: Enhancing unsupervised grammatical error correction with instruction tuning,\u201d in Proceedings of the 31 st  International Conference on Computational Linguistics, O. Rambow, L. Wanner, M. Apidianaki, H. Al-Khalifa, B. D. Eugenio, and S. Schockaert, Eds. Abu Dhabi, UAE: Association for Computational Linguistics, Jan. 2025, pp. 110\u2013122. [Online]. Available: https:\/\/aclanthology.org\/2025.coling-main.9\/."},{"key":"null","unstructured":"M. Yasunaga, J. Leskovec, and P. Liang, \u201cLm-critic: Language models for unsupervised grammatical error correction,\u201d arXiv preprint arXiv:2109.06822, 2021."},{"key":"null","unstructured":"Z. Du, Y. Qian, X. Liu, M. Ding, J. Qiu, Z. Yang, and J. Tang, \u201cGLM: General language model pretraining with autoregressive blank infilling,\u201d in Proceedings of the 60 th  Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), S. Muresan, P. Nakov, and A. Villavicencio, Eds. Dublin, Ireland: Association for Computational Linguistics, May 2022, pp. 320\u2013335. [Online]. Available: https:\/\/aclanthology.org\/2022.acl-long.26\/."},{"key":"null","unstructured":"H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y. Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale et al., \u201cLlama 2: Open foundation and fine-tuned chat models,\u201d arXiv preprint arXiv:2307.09288, 2023."},{"key":"null","unstructured":"W. Li and H. Wang, \u201cDetection-correction structure via general language model for grammatical error correction,\u201d arXiv preprint arXiv:2405.17804, 2024."},{"key":"null","unstructured":"R. Sennrich, B. Haddow, and A. Birch, \u201cNeural machine translation of rare words with subword units,\u201d in Proceedings of the 54 th  annual meeting of the association for computational linguistics (volume 1: long papers), 2016, pp. 1715\u20131725."},{"key":"null","unstructured":"M. Lewis, Y. Liu, N. Goyal, M. Ghazvininejad, A. Mohamed, O. Levy, V. Stoyanov, and L. Zettlemoyer, \u201cBART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension,\u201d in Proceedings of the 58 th  Annual Meeting of the Association for Computational Linguistics, D. Jurafsky, J. Chai, N. Schluter, and J. Tetreault, Eds. Online: Association for Computational Linguistics, Jul. 2020, pp. 7871\u20137880. [Online]. Available: https:\/\/aclanthology.org\/2020.acl-main.703\/."},{"key":"null","unstructured":"Y. Liu, J. Gu, N. Goyal, X. Li, S. Edunov, M. Ghazvininejad, M. Lewis, and L. Zettlemoyer, \u201cMultilingual denoising pre-training for neural machine translation,\u201d Transactions of the Association for Computational Linguistics, vol. 8, pp. 726\u2013742, 2020."},{"key":"null","unstructured":"T. Kudo and J. Richardson, \u201cSentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing,\u201d arXiv preprint arXiv:1808.06226, 2018."},{"key":"null","unstructured":"L. Yang, H. Li, L. Li, C. Xu, S. Xia, and C. Yuan, \u201cLET: Leveraging error type information for grammatical error correction,\u201d in Findings of the Association for Computational Linguistics: ACL 2023, A. Rogers, J. Boyd-Graber, and N. Okazaki, Eds. Toronto, Canada: Association for Computational Linguistics, Jul. 2023, pp. 5986\u20135998. [Online]. Available: https:\/\/aclanthology.org\/2023.findings-acl.371\/."},{"key":"null","unstructured":"P. Koehn, \u201cStatistical significance tests for machine translation evaluation,\u201d in Proceedings of the 2004 conference on empirical methods in natural language processing, 2004, pp. 388\u2013395."},{"key":"null","unstructured":"Z. Zhao and H. Wang, \u201cMaskgec: Improving neural grammatical error correction via dynamic masking,\u201d in Proceedings of the AAAI conference on artificial intelligence, vol. 34, no. 01, 2020, pp. 1226\u20131233."},{"key":"null","unstructured":"Y. He, G. Meng, K. Chen, X. Hu, and J. He, \u201cTowards security threats of deep learning systems: A survey,\u201d IEEE Transactions on Software Engineering, vol. 48, no. 5, pp. 1743\u20131770, 2020."},{"key":"null","unstructured":"S. Hisamoto, M. Post, and K. Duh, \u201cMembership inference attacks on sequence-to-sequence models: Is my data in your machine translation system?\u201d Transactions of the Association for Computational Linguistics, vol. 8, pp. 49\u201363, 2020."}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/8679221CB1EF4165908FF1032EDC3BCF","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0110","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/8679221CB1EF4165908FF1032EDC3BCF","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T01:25:25Z","timestamp":1781313925000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0110"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":80,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,9,22]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.3724\/2096-7004.di.2025.0110","relation":{},"ISSN":["2096-7004"],"issn-type":[{"value":"2096-7004","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9,22]]}}}