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.

Text matching is the task of matching two texts and determining the relationship between them, which has extensive applications in natural language processing tasks such as reading comprehension, and Question-Answering systems. The mainstream approach is to compute text representations or to interact with the text through attention mechanism, which is effective in text matching tasks. However, the performance of these models is insufficient for texts that require commonsense knowledge-based reasoning. To this end, in this paper, We introduce a new model for text matching called the Knowledge Enhanced Text Matching model (KETM), to enrich contextual representations with real-world common-sense knowledge from external knowledge sources to enhance our model understanding and reasoning. First, we use Wiktionary to retrieve the text word definitions as our external knowledge. Secondly, we feed text and knowledge to the text matching module to extract their feature vectors. The text matching module is used as an interaction module by integrating the encoder layer, the co-attention layer, and the aggregation layer. Specifically, the interaction process is iterated several times to obtain in-depth interaction information and extract the feature vectors of text and knowledge by multi-angle pooling. Then, we fuse text and knowledge using a gating mechanism to learn the ratio of text and knowledge fusion by a neural network that prevents noise generated by knowledge. After that, experimental validation on four datasets are carried out, and the experimental results show that our proposed model performs well on all four datasets, and the performance of our method is improved compared to the base model without adding external knowledge, which validates the effectiveness of our proposed method.