Abstract
Based on an exponentially increasing number of academic articles, discovering and citing comprehensive and appropriate resources has become a non-trivial task. Conventional citation recommender methods suffer from severe information loss. For example, they do not consider the section on which a user is working, the relatedness between words, or the importance of words. These shortcomings make such methods insufficient for recommending adequate citations when working on manuscripts. In this study, we propose a novel approach called dual attention model for citation recommendation (DACR) to recommend citations during manuscript preparation. Our method considers three dimensions of information: contextual words, structural contexts, and the section on which a user is working. The core of the proposed model is composed of self-attention and additive attention, where the former aims to capture the relatedness between input information, and the latter aims to learn the importance of inputs. The experiments on real-world datasets demonstrate the effectiveness of the proposed approach.
Abstract (translated)
URL
https://arxiv.org/abs/2010.00182
