Content-Based Citation Recommendation

Abstract

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 (http://labs.semanticscholar.org/citeomatic/) for citation recommendation based on our method, and a new dataset OpenCorpus of 7 million research articles to facilitate future research on this task.

NAACL 2018

References in corpus (1)

• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)

Cited by in corpus (6)

• Pretrained Transformers for Text Ranking: BERT and Beyond
• A Scalable Hybrid Research Paper Recommender System for Microsoft Academic
• Construction of the Literature Graph in Semantic Scholar
• A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications
• A New Citation Recommendation Strategy Based on Term Functions in Related Studies Section
• Navigation-Based Candidate Expansion and Pretrained Language Models for Citation Recommendation