Content-Based Citation Recommendation

By Chandra Bhagavatula, Sergey Feldman, Russell Power, Bridger Waleed Ammar. 2018

183 citations recorded by the source corpus.

We present a content-based method for recommending citations in an academic paper draft. We embed a given query document into a vector space, then use its nearest neighbors as candidates, and rerank the candidates using a discriminative model trained to distinguish between observed and unobserved citations. 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 favors self-citations which are less useful in a citation recommendation setup. We release an online portal for citation recommendation based on our method, (URL: http://bit.ly/citeDemo) and a new dataset OpenCorpus of 7 million research articles to facilitate future research on this task.

Subfields: Artificial Intelligence, Information Retrieval & Search, Natural Language Processing

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 Retrieval & Search

In Natural Language Processing

Citations in the corpus

Improving Wikipedia verifiability with AI (2022, background): “More broadly, citation retrieval and paper/source recommendation have also received attention in the scientific literature domain for many decades (McNee et al., 2002; Ren et al., 2014; Bhagavatula et al., 2018; Chou et al., 2020), albeit with less of a focus on verifiability of existing citations, ”
S2ORC: The Semantic Scholar Open Research Corpus (2020, methodology): “2019) and document-level (Yu et al., 2012; Liu et al., 2015; Bhagavatula et al., 2018) citation recommendation.”
GORC: A large contextual citation graph of academic papers (2019, background): “In-line citation recommendation is related to the broader task of suggesting relevant references for an overall document (Bhagavatula et al., 2018; Liu et al., 2015; Yu et al., 2012), with some previous work incorporating citation contexts as training data.”
Construction of the Literature Graph in Semantic Scholar (2018, background): “Also related is the problem of predicting which papers should be cited in a given draft (Bhagavatula et al., 2018), which can help improve the quality of a paper draft before it is submitted for peer review, or used to supplement the list of references after a paper is published.”
LinkBERT: Pretraining Language Models with Document Links (2022, methodology): “Citation links are often used to improve summarization and recommendation of academic papers (Qazvinian & Radev, 2008; Yasunaga et al., 2019; Bhagavatula et al., 2018; Khadka et al., 2020; Cohan et al., 2020).”
Citation recommendation: approaches and datasets (2020, unknown): “[21] NAACL’18 Kobayashi et al.”
A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications (2018, background): “Tools like Citeomatic 29 (Bhagavatula et al., 2018) are especially useful in ﬁnding relevant articles not cited in the manuscript.”
SPECTER: Document-level Representation Learning using Citation-informed Transformers (2020, methodology): “We also compare with Citeomatic (Bhagavatula et al., 2018), a closely related paper representation model for citation prediction which trains content-based representations with citation graph information via dynamically”