SentCite: a sentence-level citation recommender based on the salient similarity among multiple segments

Efficiently making adequate citations is becoming more challenging due to the rapidly increasing volume of publications. In practice, citing the appropriate references is a time-consuming and skill-required task. Accordingly, many studies have tried to help by providing citation-oriented support. In this field, citation recommendation is a significant research area because it addresses the problems of required profound skills and information overload. In this paper, we propose a sentence-level citation recommender, SentCite, that can identify the sentences that need links to references and can recommend citations. SentCite employs the convolutional recurrent neural network to extract the citing sentences and recommends citations based on the salient similarity between the sentences among the abstract, full text, and in-link context of the target papers. Unlike some other research in the big data domain, the recommended quality papers in this application are very limited. We proposed undersampling inlink context awareness to avoid overfitting problems. SentCite can recommend the most appropriate papers for the given sentences and outperforms other context-based methods in terms of improvement in mean reciprocal rank (MRR) 31.8%, mean average precision (MAP) 30.1%, and normalized discounted cumulative gain (NDCG) 33.8%.

Automated summary

This paper proposes SentCite, a sentence-level citation recommender that can identify sentences that need citations and recommend them. By utilizing convolutional recurrent neural network and salient similarity between the sentences and in-link context, SentCite outperforms other methods in terms of improvement in mean reciprocal rank, mean average precision, and normalized discounted cumulative gain.