A Multi-task based Bilateral-Branch Network for Imbalanced Citation Intent Classification

Identifying the purpose of citations plays an important role in evaluating the impact of the literature. There is a data imbalanced problem on different types of citation intents which harms the performance of the classification model. To alleviate this problem, We adapt the bilateral-branch network proposed in the computer vision domain to our topic in the natural language processing domain by constructing shared and non-shared encoder layers using pre-trained language model and word attention layer respectively. In addition, to learn rich representations by leveraging the auxiliary information, we propose a multi-task based bilateral-branch network. On the issue of how to integrate multi-task model and bilateral-branch network, because one advantage of multi-task learning is using more data or information to learn better representations, we propose a solution of integrating the networks of the auxiliary tasks with the representation learning branch of the bilateral- branch network. The experimental results show that our model outperforms other models used for citation intent classification.