GeLaiGeLai: A visual platform for analysis of Classical Chinese Poetry based on Knowledge Graph

Abstract

Classical Chinese poetry contains many precious historical and cultural information. However, the knowledge of classical Chinese poetry is highly fragmented. The statistics of imageries and allusions are often incomplete. Most of related works do not analyse the knowledge of poetry from the perspective of archaic Chinese words. It is hard to determine whether words are semantically related. Therefore, to solve these problems, “GeLaiGeLai” has been set up here, which is a system for data analysis of classical Chinese poetry based on knowledge graph. On the one hand, the platform is able to quickly and accurately find new words in ancient Chinese corpus through AP-LSTM-CRF, which is a new word detection method that first generates frequent character sequences using improved Apriori algorithm and then uses Bi-LSTM-CRF model which could generate the segmentation probability of every position of the sentence to further judge whether each frequent character sequence is a true new word. On the other hand, we visualize the knowledge graph and analyse the commonly-used word and emotions of poets. At the same time, the platform complements the characteristics of poetry, using knowledge graph to solve the problem of knowledge fragmentation and making it more systematic. With the knowledge graph, the performance of many reasoning and analysis tasks about classical Chinese poetry can be improved, such as determining the theme of poetry and analyzing the emotion of poetry, which proves the knowledge graph is helpful to understand classical Chinese poetry.