SVD-CNN: A Convolutional Neural Network Model with Orthogonal Constraints Based on SVD for Context-Aware Citation Recommendation.

Shaoyu Tao,Li Zhu,Chaoyuan Shen,Tao Dai,Giosuè Lo Bosco

doi:10.1155/2020/5343214

Shaoyu Tao, Li Zhu + Show 3 more

Open Access

https://doi.org/10.1155/2020/5343214

Copy DOI

Abstract

Context-aware citation recommendation aims to automatically predict suitable citations for a given citation context, which is essentially helpful for researchers when writing scientific papers. In existing neural network-based approaches, overcorrelation in the weight matrix influences semantic similarity, which is a difficult problem to solve. In this paper, we propose a novel context-aware citation recommendation approach that can essentially improve the orthogonality of the weight matrix and explore more accurate citation patterns. We quantitatively show that the various reference patterns in the paper have interactional features that can significantly affect link prediction. We conduct experiments on the CiteSeer datasets. The results show that our model is superior to baseline models in all metrics.

Highlights

Citation recommendation for researchers to quickly find the appropriate relevant literature is a rapidly developing research area [1]
Similar to other NLP tasks (e.g., information retrieval (IR) and text mining), the simplest solution for contextaware citation recommendation calculates the relevant score between a citation context and candidate papers via Euclidean distance [3] and selects the salient citations
Brock et al [22] used orthogonal regularization to improve the generalization performance of image generation editor tasks by using generative adversarial networks (GANs) [23]. ey further expanded their work into BigGAN [24]. e results in their work showed that by applying orthogonal regularization, the generator allows fine-tuning the tradeoff between fidelity and diversity of samples by truncating hidden spaces, which can make the model achieve the best performance in the image synthesis of class conditions

Summary

Introduction

Citation recommendation for researchers to quickly find the appropriate relevant literature is a rapidly developing research area [1]. E key problem for context-aware citation recommendation is how to measure the similarity between the citation context and a specific scientific paper. The weight vectors in existing neural network-based models are usually strongly correlated. E above problems seriously affect the performance of citation recommendation because citing activity appears to have strong orthogonality. “Math-reference” usually appears in the main part of the paper describing the researcher’s method in detail, and its citations will be more related to mathematical theorem. In the Computational Intelligence and Neuroscience neural network model, these three citation types are usually mapped into a matrix and can be seen as base vectors for inputs.

Methods

Results

Conclusion