@inproceedings{bhagavatula-etal-2018-content,
title = "Content-Based Citation Recommendation",
author = "Bhagavatula, Chandra and
Feldman, Sergey and
Power, Russell and
Ammar, Waleed",
editor = "Walker, Marilyn and
Ji, Heng and
Stent, Amanda",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-1022/",
doi = "10.18653/v1/N18-1022",
pages = "238--251",
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 for citation recommendation based on our method, (URL: \url{http://bit.ly/citeDemo}) and a new dataset OpenCorpus of 7 million research articles to facilitate future research on this task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhagavatula-etal-2018-content">
<titleInfo>
<title>Content-Based Citation Recommendation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chandra</namePart>
<namePart type="family">Bhagavatula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergey</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Russell</namePart>
<namePart type="family">Power</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Waleed</namePart>
<namePart type="family">Ammar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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 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.</abstract>
<identifier type="citekey">bhagavatula-etal-2018-content</identifier>
<identifier type="doi">10.18653/v1/N18-1022</identifier>
<location>
<url>https://aclanthology.org/N18-1022/</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>238</start>
<end>251</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Content-Based Citation Recommendation
%A Bhagavatula, Chandra
%A Feldman, Sergey
%A Power, Russell
%A Ammar, Waleed
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F bhagavatula-etal-2018-content
%X 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.
%R 10.18653/v1/N18-1022
%U https://aclanthology.org/N18-1022/
%U https://doi.org/10.18653/v1/N18-1022
%P 238-251
Markdown (Informal)
[Content-Based Citation Recommendation](https://aclanthology.org/N18-1022/) (Bhagavatula et al., NAACL 2018)
ACL
- Chandra Bhagavatula, Sergey Feldman, Russell Power, and Waleed Ammar. 2018. Content-Based Citation Recommendation. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 238–251, New Orleans, Louisiana. Association for Computational Linguistics.