We address automatic citation sentence generation, which reduces the burden on writing scientific papers. For highly accurate citation senetence generation, appropriate language must be learned using information such as the relationship between the cited source and the cited paper as well as the context in which the paper cited. Although the abstracts of papers have been used for the generation in the past, they often contain extra information in the citation sentence, which might negatively impact the generation of citation sentences. Therefore, this study attempts to learn a highly accurate citation sentence generation model using sentences from cited articles that resemble the previous sentence to the cited location, thereby utilizing information that is more useful for citation sentence generation.

With the increase in the number of published academic papers, growing expectations have been placed on research related to supporting the writing process of scientific papers. Recently, research has been conducted on various tasks such as citation worthiness (judging whether a sentence requires citation), citation recommendation, and citation-text generation. However, since each task has been studied and evaluated using data that has been independently developed, it is currently impossible to verify whether such tasks can be successfully pipelined to effective use in scientific-document writing. In this paper, we first define a series of tasks related to scientific-document writing that can be pipelined. Then, we create a dataset of academic papers that can be used for the evaluation of each task as well as a series of these tasks. Finally, using the dataset, we evaluate the tasks of citation worthiness and citation recommendation as well as both of these tasks integrated. The results of our evaluations show that the proposed approach is promising.