With English as the dominant global language, demand for precise grammar processing grows rapidly. Traditional methods struggle with complex grammatical structures, especially for non-native speakers. To address this, we propose a deep neural network (DNN) and transfer learning-based system for automated English grammar parsing and correction. Our approach: (1) Uses Transformer-based DNNs to capture intricate grammar patterns from large corpora; (2) Applies transfer learning to adapt generic linguistic knowledge to specialized error correction; (3) Achieves 10% higher accuracy and 8% better recall than traditional tools. Critically, it handles complex errors like subject-verb disagreement and tense misuse with high robustness.
CariowACariowaG. Fast algorithms for deep octonion networks. IEEE Trans Neural Netw Learn Syst2023; 34(1): 543–548.
2.
Daniela Lupu and Ion Necoara. Exact representation and efficient approximations of linear model predictive control laws via HardTanh type deep neural networks. Syst Control Lett2024; 186: 105742.
3.
HuGDixitCQiG. Discriminative shape feature pooling in deep neural networks. J Imaging2022; 8(5): 118.
4.
KongFWangXPuK, et al.A practical non-profiled deep-learning-based power analysis with hybrid-supervised neural networks. Electronics2023; 12(15): 3361.
5.
Abdallah Abu Qub’a, Mohammed Nour Abu GubaFarehSFarehS. Exploring the use of grammarly in assessing English academic writing. Heliyon2024; 10(15): e34893.
6.
PhanTDoP. A novel framework to enhance the performance of training distributed deep neural networks. Intell Data Anal2023; 27(3): 753–768.
7.
PengWVarankaTMostafaA, et al.Hyperbolic deep neural networks: a survey. IEEE Trans Pattern Anal Mach Intell2022; 44(12): 10023–10044.
8.
TanwarAKumar VishwakarmaD. A deep neural network-based hybrid recommender system with user-user networks. Multimed Tools Appl2023; 82(10): 15613–15633.
9.
ZangKWuWLuoW. Deep sparse learning for automatic modulation classification using recurrent neural networks. Sensors2021; 21(19): 6410.
10.
FarrellMHLiangTMisraS. Deep neural networks for estimation and inference. Econometrica2021; 89(1): 181–213.
11.
ZhouYYenGGYiZ. Evolutionary shallowing deep neural networks at block levels. IEEE Trans Neural Netw Learn Syst2022; 33(9): 4635–4647.
12.
ZhangBLinH. Functional loops: monitoring functional organization of deep neural networks using algebraic topology. Neural Netw2024; 174: 106239.
13.
WrightLGOnoderaTSteinMM, et al.Deep physical neural networks trained with backpropagation. Nature2022; 601(7894): 549–555.
14.
WangLZhangYYuanJ, et al.FEBDNN: fusion embedding-based deep neural network for user retweeting behavior prediction on social networks. Neural Comput Appl2022; 34(16): 13219–13235.
15.
LiZZhangSLiH, et al.On-line transfer learning for multi-fidelity data fusion with ensemble of deep neural networks. Adv Eng Inform2022; 53: 101689.
16.
PoyatosJMolinaDMartínez-SerasA, et al.Multiobjective evolutionary pruning of deep neural networks with transfer learning for improving their performance and robustness. Appl Soft Comput2023; 147: 110757.
17.
YangTYuXMaN, et al.Deep representation-based transfer learning for deep neural networks. Knowl Base Syst2022; 253: 109526.
18.
JiangWLvS. Hierarchical deployment of deep neural networks based on fog computing inferred acceleration model. Clust Comput2021; 24(4): 2807–2817.
19.
ChenQShiboSRongpengL, et al.An efficient pruning scheme of deep neural networks for internet of things applications. EURASIP J Appl Signal Process2021; 2021(1): 120961.
20.
LiuYLiD. AdaXod: a new adaptive and momental bound algorithm for training deep neural networks. J Supercomput2023; 79(15): 17691–17715.
21.
BaoGSongZXuR. Prescribed attractivity region selection for current neural networks based on deep reinformation learning. Neural Comput Appl2024; 36(5): 2399–2409.
22.
YangXZhouJZhangQ, et al.Evaluation and interpretation of runoff forecasting models based on hybrid deep neural networks. Water Resour Manag2024; 38(6): 1987–2013.
23.
LiangYPengWZhengZ-J, et al.A hybrid quantum-classic neural network with deep residual learning. Neural Netw2021; 143: 133–147.
24.
ChenLHuangHChenD. Join cardinality estimation by combining operator-level deep neural networks. Inf Sci2021; 546: 1047–1062.
25.
Rasheed RababaahA. Wind turbine signal fault diagnosis using deep neural networks-inspired model. Int J Comput Appl Technol2022; 69(4): 365–376.
26.
BannòSMatassoniM. Back to grammar: using grammatical error correction to automatically assess L2 speaking proficiency. Speech Commun2024; 157: 103025.
27.
WangY. E-learning application in English writing classroom based on neural machine translation and semantic analysis algorithms. Entertain Comput2024; 51: 100730.
28.
BalaZZambukFUYa'u ImamB, et al.Transfer learning approach for malware images classification on android devices using deep convolutional neural network. Procedia Comput Sci2022; 212: 429–440.
29.
Souvik Chakraborty. Transfer learning based multi-fidelity physics informed deep neural network. J Comput Phys2021; 426: 109942.
30.
HungJCChangJ-W. Multi-level transfer learning for improving the performance of deep neural networks: theory and practice from the tasks of facial emotion recognition and named entity recognition. Appl Soft Comput2021; 109: 107491.
