摘要：Researchers may describe different aspects of past scientific publications in their publications and the descriptions may keep changing in the evolution of science. The diverse and changing descriptions (i.e., citation context) on a publication characterize the impact and contributions of the past publication. In this article, we aim to provide an approach to understanding the changing roles of a publication characterized by its citation context in the full text of publications. We proposed approaches for representing the changing citation context of cited publications in different periods as sequences of vectors by training temporal embedding models. We can utilize the temporal representations to quantify how much the roles of publications changed and interpret how they changed. We also evaluated the performance of three ways of constructing citation context for representation learning. Our study in the biomedical domain shows that our metric on the changes of publication roles is stable at the population level but it can account for the variation of individual publications.
