@inproceedings{molloy-etal-2020-virtual,
title = "Virtual Citation Proximity ({VCP}): Empowering Document Recommender Systems by Learning a Hypothetical In-Text Citation-Proximity Metric for Uncited Documents",
author = "Molloy, Paul and
Beel, Joeran and
Aizawa, Akiko",
editor = "Knoth, Petr and
Stahl, Christopher and
Gyawali, Bikash and
Pride, David and
Kunnath, Suchetha N. and
Herrmannova, Drahomira",
booktitle = "Proceedings of the 8th International Workshop on Mining Scientific Publications",
month = "05 " # aug,
year = "2020",
address = "Wuhan, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wosp-1.1",
pages = "1--8",
abstract = "The relatedness of research articles, patents, court rulings, web pages, and other document types is often calculated with citation or hyperlink-based approaches like co-citation (proximity) analysis. The main limitation of citation-based approaches is that they cannot be used for documents that receive little or no citations. We propose Virtual Citation Proximity (VCP), a Siamese Neural Network architecture, which combines the advantages of co-citation proximity analysis (diverse notions of relatedness / high recommendation performance), with the advantage of content-based filtering (high coverage). VCP is trained on a corpus of documents with textual features, and with real citation proximity as ground truth. VCP then predicts for any two documents, based on their title and abstract, in what proximity the two documents would be co-cited, if they were indeed co-cited. The prediction can be used in the same way as real citation proximity to calculate document relatedness, even for uncited documents. In our evaluation with 2 million co-citations from Wikipedia articles, VCP achieves an MAE of 0.0055, i.e. an improvement of 20{\%} over the baseline, though the learning curve suggests that more work is needed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="molloy-etal-2020-virtual">
<titleInfo>
<title>Virtual Citation Proximity (VCP): Empowering Document Recommender Systems by Learning a Hypothetical In-Text Citation-Proximity Metric for Uncited Documents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Molloy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joeran</namePart>
<namePart type="family">Beel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Aizawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05 aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th International Workshop on Mining Scientific Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Knoth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Stahl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bikash</namePart>
<namePart type="family">Gyawali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Pride</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suchetha</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Kunnath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Drahomira</namePart>
<namePart type="family">Herrmannova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Wuhan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The relatedness of research articles, patents, court rulings, web pages, and other document types is often calculated with citation or hyperlink-based approaches like co-citation (proximity) analysis. The main limitation of citation-based approaches is that they cannot be used for documents that receive little or no citations. We propose Virtual Citation Proximity (VCP), a Siamese Neural Network architecture, which combines the advantages of co-citation proximity analysis (diverse notions of relatedness / high recommendation performance), with the advantage of content-based filtering (high coverage). VCP is trained on a corpus of documents with textual features, and with real citation proximity as ground truth. VCP then predicts for any two documents, based on their title and abstract, in what proximity the two documents would be co-cited, if they were indeed co-cited. The prediction can be used in the same way as real citation proximity to calculate document relatedness, even for uncited documents. In our evaluation with 2 million co-citations from Wikipedia articles, VCP achieves an MAE of 0.0055, i.e. an improvement of 20% over the baseline, though the learning curve suggests that more work is needed.</abstract>
<identifier type="citekey">molloy-etal-2020-virtual</identifier>
<location>
<url>https://aclanthology.org/2020.wosp-1.1</url>
</location>
<part>
<date>2020-05 aug</date>
<extent unit="page">
<start>1</start>
<end>8</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Virtual Citation Proximity (VCP): Empowering Document Recommender Systems by Learning a Hypothetical In-Text Citation-Proximity Metric for Uncited Documents
%A Molloy, Paul
%A Beel, Joeran
%A Aizawa, Akiko
%Y Knoth, Petr
%Y Stahl, Christopher
%Y Gyawali, Bikash
%Y Pride, David
%Y Kunnath, Suchetha N.
%Y Herrmannova, Drahomira
%S Proceedings of the 8th International Workshop on Mining Scientific Publications
%D 2020
%8 05 aug
%I Association for Computational Linguistics
%C Wuhan, China
%F molloy-etal-2020-virtual
%X The relatedness of research articles, patents, court rulings, web pages, and other document types is often calculated with citation or hyperlink-based approaches like co-citation (proximity) analysis. The main limitation of citation-based approaches is that they cannot be used for documents that receive little or no citations. We propose Virtual Citation Proximity (VCP), a Siamese Neural Network architecture, which combines the advantages of co-citation proximity analysis (diverse notions of relatedness / high recommendation performance), with the advantage of content-based filtering (high coverage). VCP is trained on a corpus of documents with textual features, and with real citation proximity as ground truth. VCP then predicts for any two documents, based on their title and abstract, in what proximity the two documents would be co-cited, if they were indeed co-cited. The prediction can be used in the same way as real citation proximity to calculate document relatedness, even for uncited documents. In our evaluation with 2 million co-citations from Wikipedia articles, VCP achieves an MAE of 0.0055, i.e. an improvement of 20% over the baseline, though the learning curve suggests that more work is needed.
%U https://aclanthology.org/2020.wosp-1.1
%P 1-8
Markdown (Informal)
[Virtual Citation Proximity (VCP): Empowering Document Recommender Systems by Learning a Hypothetical In-Text Citation-Proximity Metric for Uncited Documents](https://aclanthology.org/2020.wosp-1.1) (Molloy et al., WOSP 2020)
ACL