Hybrid Data Augmentation for Citation Function Classification

The citation function generally signifies the purpose or reason underlying a citation within a scholarly paper or a research article. Automatic citation function classification is, therefore, a task in computational linguistics and information science that can facilitate further applications in reference research, citation recommendation, and evaluation of research activities. By taking into account the state of the art, we identify two major constraints pertinent to the data of the citation function classification task, i.e., data imbalance and data sparsity. On the one hand, the natural distribution of different types of citations in one scientific literature is uneven leading to data imbalance in the real scenario. On the other hand, the citation function data is generally labeled by an expert which takes huge human effort resulting in a limited data scale. To this end, in this paper, we propose HybridDA, a two-stage model based on GPT-2 data argumentation and data retrieval to synthesize more high-quality annotated citation function data in a bid to solve both data imbalance and data sparsity problems. We conduct experiments on imbalance setting and low resource setting with our proposed approach. The experimental results on both of these settings demonstrate that our proposed model can achieve competitive performance in contrast to the other baseline models.