A Context-Aware Citation Recommendation Model with BERT and Graph Convolutional Networks

TL;DR

This paper introduces a deep learning model combining BERT and GCN for context-aware citation recommendation, along with a new well-organized dataset, achieving state-of-the-art performance with significant improvements.

Contribution

The paper presents a novel deep learning model and a new dataset for context-aware citation recommendation, addressing previous limitations in dataset organization and model performance.

Findings

Achieved over 28% improvement in MAP and recall@k

Proposed a new dataset called FullTextPeerRead

Attained state-of-the-art performance in citation recommendation

Abstract

With the tremendous growth in the number of scientific papers being published, searching for references while writing a scientific paper is a time-consuming process. A technique that could add a reference citation at the appropriate place in a sentence will be beneficial. In this perspective, context-aware citation recommendation has been researched upon for around two decades. Many researchers have utilized the text data called the context sentence, which surrounds the citation tag, and the metadata of the target paper to find the appropriate cited research. However, the lack of well-organized benchmarking datasets and no model that can attain high performance has made the research difficult. In this paper, we propose a deep learning based model and well-organized dataset for context-aware paper citation recommendation. Our model comprises a document encoder and a context encoder, which uses Graph Convolutional Networks (GCN) layer and Bidirectional Encoder Representations from Transformers (BERT), which is a pre-trained model of textual data. By modifying the related PeerRead dataset, we propose a new dataset called FullTextPeerRead containing context sentences to cited references and paper metadata. To the best of our knowledge, This dataset is the first well-organized dataset for context-aware paper recommendation. The results indicate that the proposed model with the proposed datasets can attain state-of-the-art performance and achieve a more than 28% improvement in mean average precision (MAP) and recall@k.