@inproceedings{vajdecka-etal-2023-predicting,
title = "Predicting the presence of inline citations in academic text using binary classification",
author = "Vajdecka, Peter and
Callegari, Elena and
Xhura, Desara and
{\'A}smundsson, Atli",
editor = {Alum{\"a}e, Tanel and
Fishel, Mark},
booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may,
year = "2023",
address = "T{\'o}rshavn, Faroe Islands",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2023.nodalida-1.72",
pages = "717--722",
abstract = "Properly citing sources is a crucial component of any good-quality academic paper. The goal of this study was to determine what kind of accuracy we could reach in predicting whether or not a sentence should contain an inline citation using a simple binary classification model. To that end, we fine-tuned SciBERT on both an imbalanced and a balanced dataset containing sentences with and without inline citations. We achieved an overall accuracy of over 0.92, suggesting that language patterns alone could be used to predict where inline citations should appear with some degree of accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vajdecka-etal-2023-predicting">
<titleInfo>
<title>Predicting the presence of inline citations in academic text using binary classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Vajdecka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Callegari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desara</namePart>
<namePart type="family">Xhura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atli</namePart>
<namePart type="family">Ásmundsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanel</namePart>
<namePart type="family">Alumäe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tórshavn, Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Properly citing sources is a crucial component of any good-quality academic paper. The goal of this study was to determine what kind of accuracy we could reach in predicting whether or not a sentence should contain an inline citation using a simple binary classification model. To that end, we fine-tuned SciBERT on both an imbalanced and a balanced dataset containing sentences with and without inline citations. We achieved an overall accuracy of over 0.92, suggesting that language patterns alone could be used to predict where inline citations should appear with some degree of accuracy.</abstract>
<identifier type="citekey">vajdecka-etal-2023-predicting</identifier>
<location>
<url>https://aclanthology.org/2023.nodalida-1.72</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>717</start>
<end>722</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting the presence of inline citations in academic text using binary classification
%A Vajdecka, Peter
%A Callegari, Elena
%A Xhura, Desara
%A Ásmundsson, Atli
%Y Alumäe, Tanel
%Y Fishel, Mark
%S Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2023
%8 May
%I University of Tartu Library
%C Tórshavn, Faroe Islands
%F vajdecka-etal-2023-predicting
%X Properly citing sources is a crucial component of any good-quality academic paper. The goal of this study was to determine what kind of accuracy we could reach in predicting whether or not a sentence should contain an inline citation using a simple binary classification model. To that end, we fine-tuned SciBERT on both an imbalanced and a balanced dataset containing sentences with and without inline citations. We achieved an overall accuracy of over 0.92, suggesting that language patterns alone could be used to predict where inline citations should appear with some degree of accuracy.
%U https://aclanthology.org/2023.nodalida-1.72
%P 717-722
Markdown (Informal)
[Predicting the presence of inline citations in academic text using binary classification](https://aclanthology.org/2023.nodalida-1.72) (Vajdecka et al., NoDaLiDa 2023)
ACL