Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Oct 22:2020:5343214.
doi: 10.1155/2020/5343214. eCollection 2020.

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

Shaoyu Tao  1 , Chaoyuan Shen  1 , Li Zhu  1 , Tao Dai  1
Affiliations

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

Shaoyu Tao et al. Comput Intell Neurosci. .

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.

PubMed Disclaimer

Conflict of interest statement

The authors declare that there are no conflicts of interest regarding the publication of this paper.

Figures

Figure 1
Figure 1
Distribution of the weight vector of the reference type in geometric space.
Figure 2
Figure 2
An overview of our model.
Figure 3
Figure 3
Convolution extraction generates phrases.
Figure 4
Figure 4
“W-ap” structure.
Figure 5
Figure 5
“All-ap” structure.
Figure 6
Figure 6
Generating the feature map.
Figure 7
Figure 7
SVD-FC layer.
Figure 8
Figure 8
Comparison of recall with different methods on CiteSeer.
Figure 9
Figure 9
Comparison of MRR, MAP, and nDCG with different methods on CiteSeer.
Figure 10
Figure 10
The change in S(W) during training on unmixed datasets and mixed datasets.
Figure 11
Figure 11
The performance impact of sot on CiteSeer.
Figure 12
Figure 12
The performance impact of d0 on CiteSeer.
See this image and copyright information in PMC

References

    1. Angrosh M. A., Cranefield S., Stanger N. Conditional random field based sentence context identification: enhancing citation services for the research community. Proceedings of the First Australasian Web Conference; January 2013; Adelaide, Australia.
    1. He Q., Pei J., Kifer D., et al. Context-aware citation recommendation. Proceedings of the International Conference on World Wide Web; April 2010; Raleigh, NC, USA.
    1. He Q., Kifer D., Pei J., et al. Citation recommendation without author supervision. Proceedings of the Fourth ACM international Conference on Web Search and Data Mining; February 2011; Hong Kong, China.
    1. Huang W. A neural probabilistic model for context based citation recommendation. Proceedings of the AAAI Conference on Artificial Intelligence; January 2015; Austin, TX, USA.
    1. Tan J., Wan X., Xiao J. A neural network approach to quote recommendation in writings. Proceedings of the ACM International on Conference on Information and Knowledge Management; October 2016; Indianapolis, IN, USA.

LinkOut - more resources