A Hierarchical Korean-Chinese Machine Translation Model Based on Sentence Structure Segmentation

Machine translation attempts to understand the semantics of the original language and automatically translate text from one language to another. However, in traditional Sequence-to-Sequence (Seq2Seq) Korean-Chinese machine translation models, the performance in long sequence generation tasks is often limited, primarily due to the model’s difficulty in effectively utilizing key information in too lengthy sequences. To address this issue, we propose a hierarchical Korean-Chinese machine translation model based on Korean sentence segmentation. Utilizing the unique linguistic features and grammatical structure of Korean, we develop a segmentation method for long sequence texts to construct a hierarchical model for translating segmented sentences. Additionally, we incorporate pre-trained knowledge to enhance the integration of linguistic knowledge with the model and strengthen the connections between contexts. Experiments conducted on four Dong-A Ilbo variant datasets demonstrate that our method significantly improves the accuracy and fluency of translation compared to existing models.