%0 Conference Paper
%A Kieu, Thanh Binh
%A Unanue, Inigo Jauregi
%A Pham, Bao Son
%A Phan, Xuan Hieu
%A Piccardi, Massimo
%B The 25th International Conference on Pattern Recognition
%C Milan, Italy
%D 2020
%F SisLab:4216
%T Learning Neural Textual Representations for Citation Recommendation
%U https://eprints.uet.vnu.edu.vn/eprints/id/eprint/4216/
%X With the rapid growth of the scientific literature, manually selecting appropriate citations for a paper is becoming increasingly challenging and time-consuming. While several approaches for automated citation recommendation have been proposed in the recent years, effective document representations for citation recommendation are still elusive to a large extent. For this reason, in this paper we propose a novel approach to citation recommendation which leverages a deep sequential representation of the documents (Sentence-BERT) cascaded with Siamese and triplet networks in a submodular scoring function. To the best of our knowledge, this is the first approach to combine deep representations and submodular selection for a task of citation recommendation. Experiments have been carried out using a popular benchmark dataset - the ACL Anthology Network corpus - and evaluated against baselines and a state-of-the-art approach using metrics such as the MRR and F1-at-k score. The results show that the proposed approach has been able to outperform all the compared approaches in every measured metric.