Content-Based Citation Recommendation

  title={Content-Based Citation Recommendation},
  author={Chandra Bhagavatula and Sergey Feldman and Russell Power and Waleed Ammar},
We present a content-based method for recommending citations in an academic paper draft. [] Key Method Unlike previous work, our method does not require metadata such as author names which can be missing, e.g., during the peer review process. Without using metadata, our method outperforms the best reported results on PubMed and DBLP datasets with relative improvements of over 18% in F1@20 and over 22% in MRR. We show empirically that, although adding metadata improves the performance on standard metrics, it…

Citation recommendation: approaches and datasets

This article presents an overview of the approaches and data sets for citation recommendation and identifies differences and commonalities using various dimensions, and sheds light on the evaluation methods and outline general challenges in the evaluation and how to meet them.

Citation recommendation employing heterogeneous bibliographic network embedding

This work proposes a heterogeneous network embedding model that jointly learns node representations by exploiting semantics corresponding to the author, time, context, field of study, citations, and topics and shows significant improvement on mean average precision and normalized discounted cumulative gain metrics.

A graph-based taxonomy of citation recommendation models

This survey explores the state-of-the-art citation recommendation models which are explored using the following seven criteria: platform used, data factors/features, data representation methods, methodologies and models, recommendation types, problems addressed, and personalization.

A New Citation Recommendation Strategy Based on Term Functions in Related Studies Section

The experiments show that the term function-based methods outperform the baseline methods regarding the recall, precision, and F1-score measurement, demonstrating that term functions are useful in identifying valuable citations.

A Hybrid Approach Toward Research Paper Recommendation Using Centrality Measures and Author Ranking

The proposed method creates a multilevel citation and relationship network of authors in which the citation network uses the structural relationship between the papers to extract significant papers, and authors’ collaboration network finds key authors from those papers.

HybridCite: A Hybrid Model for Context-Aware Citation Recommendation

Evaluation results show that a hybrid model containing embedding and information retrieval-based components outperforms its individual components and further algorithms by a large margin.

Learning Neural Textual Representations for Citation Recommendation

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 and is able to outperform all the compared approaches in every measured metric.

A Collaborative Approach Toward Scientific Paper Recommendation Using Citation Context

The experimental results demonstrate that the proposed approach has significantly outperforms the baseline approaches in terms of precision, recall, F1, mean average precision, and mean reciprocal rank, which are commonly used information retrieval metrics.


This work adapts to the scientific domain a proven combination based on “bag of words” retrieval followed by re-scoring with a BERT model and introduces a novel navigation-based document expansion strategy to enrich the candidate documents processed by the neural models.

Deep learning-based citation recommendation system for patents

This study presents a novel dataset called PatentNet that includes textual information and metadata for approximately 110,000 patents from the Google Big Query service and proposes strong benchmark models considering the similarity of textual Information and metadata (such as cooperative patent classification code).



Context-Based Collaborative Filtering for Citation Recommendation

The proposed citation recommendation method significantly outperforms the baseline method in terms of precision, recall, and F1, as well as mean average precision and mean reciprocal rank, which are metrics related to the rank information in the recommendation list.

An Analysis of Citation Recommender Systems: Beyond the Obvious

This paper considers the problem of citation recommendation by extending a set of known-to-be-relevant references and proposes to combine author, venue and keyword information to interpret the citation behavior behind loosely connected papers.

ClusCite: effective citation recommendation by information network-based clustering

A novel cluster-based citation recommendation framework, called ClusCite, which explores the principle that citations tend to be softly clustered into interest groups based on multiple types of relationships in the network, and learns group memberships for objects and the significance of relevance features for each interest group by solving a joint optimization problem.

Citation recommendation without author supervision

A user simply inputs a query manuscript (without a bibliography) and the system automatically finds locations where citations are needed, and it is shown that naïve approaches do not work well due to massive noise in the document corpus.

Recommending citations: translating papers into references

This work proposes a method that "translates" research papers into references by considering the citations and their contexts from existing papers as parallel data written in two different "languages" using the translation model to create a relationship between these two "vocabularies".

A Neural Probabilistic Model for Context Based Citation Recommendation

A novel neural probabilistic model that jointly learns the semantic representations of citation contexts and cited papers is proposed that significantly outperforms other state-of-the-art models in recall, MAP, MRR, and nDCG.

A Discriminative Approach to Topic-Based Citation Recommendation

A two-layer Restricted Boltzmann Machine model, called RBM-CS, is proposed, which can discover topic distributions of paper content and citation relationship simultaneously and can significantly outperform baseline methods for citation recommendation.

A Query-oriented Approach for Relevance in Citation Networks

A two-stage query-dependent approach for retrieving relevant papers given a keyword-based query that allows for recommendations that are both highly authoritative, and also textually related to the query.

Context-aware citation recommendation

The core idea is to design a novel non-parametric probabilistic model which can measure the context-based relevance between a citation context and a document and implement a prototype system in CiteSeerX.

Citation Prediction in Heterogeneous Bibliographic Networks

A meta-path based prediction model on a topic discriminative search space is built and a two-phase citation probability learning approach is proposed, in order to predict citation relationship effectively and efficiently.