Linking Allusion Words: A Method of Combining Fine‐Grained Co‐citation Relationship and Semantic Features

Abstract

ABSTRACT It is a common phenomenon for Tang poems to cite the allusions, which can generate a rich relationship network. However, insufficient attention has been paid to investigating the relationship network. To address the research gap, by employing theories and methods of information science, this study presents a method of combining fine‐grained co‐citation relationship and semantic features to link allusion words. We constructed a fine‐grained co‐citation network between allusion words by adding cited positions and sentiments. We then transformed the fine‐grained weights into relational similarities. Moreover, we also leveraged the explanatory text as semantic information for each allusion word, mapping the semantic embedding vectors and calculating the similarities as the semantic similarities. Finally, we applied the link prediction algorithm to implement the allusion word linking. Our experimental results reveal that adding the cited positions and sentiments as well as semantic similarities can improve the performance of allusion word linking, achieving 0.869 on score. Additionally, we explore the linking results from the perspective of the shortest path and find some regular knowledge. Overall, our study extends the application of information science and promotes the development of Chinese traditional cultural resources.