Transfer Learning-Based Neural Machine Translation for Low-Resource Languages

College of Liberal Arts, Ludong University, Yantai 264025, China Chinese Lexicography Research Center, Neural Machine Translation (NMT) improves readability by augmenting sentence suggestions based on the precise likelihood words. The word are trained using learning paradigms through repeated translations, searches, and user inputs. However, challenging process is implication NMT for low-resource language wherein chances false suggestions/ substitutions high. So, this article proposes a Likelihood-based Model (LMTM) languages. model uses frequency potential from less-known sentences to identify with high precision. This achieved combination recurrence transfer learning. identified high-likelihood words used augmentation, entire set generated updates paradigm. suggests highest NMT, preventing falsification ensuring accurate translations. proposed increases 9.15%, correctness 7.46%, 7.7%, respectively. It reduces time complexity 9.33% 8.52%, Overall, LMTM translation quality