A Neural Probabilistic Model for Context Based Citation Recommendation

By Wenyi Huang, Zhaohui Wu, Chen Liang, Prasenjit Mitra, C. Lee Giles. 2015

163 citations recorded by the source corpus.

Automatic citation recommendation can be very useful for authoring a paper and is an AI-complete problem due to the challenge of bridging the semantic gap between citation context and the cited paper. It is not always easy for knowledgeable researchers to give an accurate citation context for a cited paper or to find the right paper to cite given context. To help with this problem, we propose a novel neural probabilistic model that jointly learns the semantic representations of citation contexts and cited papers. The probability of citing a paper given a citation context is estimated by training a multi-layer neural network. We implement and evaluate our model on the entire CiteSeer dataset, which at the time of this work consists of 10,760,318 citation contexts from 1,017,457 papers. We show that the proposed model significantly outperforms other state-of-the-art models in recall, MAP, MRR, and nDCG.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Deep Neural Networks for YouTube Recommendations (2016, methodology): “Neural networks are used for recommending news in [17], citations in [8] and review ratings in [20].”
S2ORC: The Semantic Scholar Open Research Corpus (2020, methodology): “Although citation contexts are no longer available through CiteSeerX, the Ref-Seer dataset (Huang et al., 2015) 18 is a dataset of short citation context snippets derived from 1.0M papers from CiteSeerX.”
Deep Learning Based Recommender System (2017, methodology): “y. Recommend rely solely on Deep Learning Integrate Deep Learning with Traditional Recommender System Tightly Coupled Model Loosely Coupled Model Models Using Single Deep Learning Techniques MLP (15) [46], [133], [2], [111] [118], [38], [9], [25] [12] [10], [65], [17], [35] [39] [66] AE (25) [82], [”
WikiRef: Wikilinks as a route to recommending appropriate references for scientific Wikipedia pages (2018, methodology): “There have been several reference recommendation systems (Huang et al., 2015; Caragea et al., 2013; Huang et al., 2014; Tang et al., 2014; Ren et al., 2014; Meng et al., 2013; Huang et al., 2012) for scientific articles but all of them either use the the text of the cited paper or the underlying cit”
Content-Based Citation Recommendation (2018, methodology): “Prior algorithms (Huang et al., 2015, 2012; Nallapati et al., 2008; Tanner and Charniak, 2015) learn an explicit representation for each training document separately that isn’t a deterministic function of the doc-ument’s words.”
A review on deep learning for recommender systems: challenges and remedies (2018, unknown): “…et al. (2016) Zuo et al. (2016) Wei et al. (2017) Ko et al. (2016) Ouyang et al. (2014) Wang et al. (2015a) Zhang et al. (2016a) Hu et al. (2014) Huang et al. (2015) Paradarami et al. (2017) Zheng et al. (2016a) Kyo-Joong et al. (2014) Yang et al. (2017) Du et al. (2017) Tang et al. (2015) Lian…”
GORC: A large contextual citation graph of academic papers (2019, methodology): “…citation recommendation (Bhagavatula et al., 2018; Liu et al., 2015; Yu et al., 2012), in-line citation recommendation (Jeong et al., 2019; Huang et al., 2015; He et al., 2010), categorizing citation intent (Cohan et al., 2019; Teufel et al., 2006), paper summarization (Cohan and…”
Citation recommendation: approaches and datasets (2020, unknown): “Secondly, operating only with papers’ metadata is also easier from a technical perspective.”