eprintid: 4158
rev_number: 9
eprint_status: archive
userid: 290
dir: disk0/00/00/41/58
datestamp: 2020-12-08 09:31:10
lastmod: 2020-12-08 09:31:10
status_changed: 2020-12-08 09:31:10
type: conference_item
metadata_visibility: show
creators_name: Kieu, Thanh Binh Thanh Binh
creators_name: Unanue, Inigo Jauregi
creators_name: Pham, Bao Son
creators_name: Phan, Xuan Hieu
creators_name: Piccardi, Massimo
creators_id: sonpb@vnu.edu.vn
creators_id: hieupx@vnu.edu.vn
title: Learning Neural Textual Representations for Citation Recommendation
ispublished: inpress
subjects: IT
abstract: 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.
date: 2020
date_type: published
official_url: https://www.micc.unifi.it/icpr2020/
full_text_status: none
pres_type: poster
event_title: The 25th International Conference on Pattern Recognition
event_location: Milan, Italy
event_type: conference
refereed: TRUE
citation:   Kieu, Thanh Binh Thanh Binh and Unanue, Inigo Jauregi and Pham, Bao Son and Phan, Xuan Hieu and Piccardi, Massimo  (2020) Learning Neural Textual Representations for Citation Recommendation.  In: The 25th International Conference on Pattern Recognition, Milan, Italy.    (In Press)