@inproceedings{kashnitsky-etal-2022-overview,
title = "Overview of the {DAGP}ap22 Shared Task on Detecting Automatically Generated Scientific Papers",
author = "Kashnitsky, Yury and
Herrmannova, Drahomira and
de Waard, Anita and
Tsatsaronis, George and
Fennell, Catriona Catriona and
Labbe, Cyril",
editor = "Cohan, Arman and
Feigenblat, Guy and
Freitag, Dayne and
Ghosal, Tirthankar and
Herrmannova, Drahomira and
Knoth, Petr and
Lo, Kyle and
Mayr, Philipp and
Shmueli-Scheuer, Michal and
de Waard, Anita and
Wang, Lucy Lu",
booktitle = "Proceedings of the Third Workshop on Scholarly Document Processing",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.sdp-1.26",
pages = "210--213",
abstract = "This paper provides an overview of the DAGPap22 shared task on the detection of automatically generated scientific papers at the Scholarly Document Process workshop colocated with COLING. We frame the detection problem as a binary classification task: given an excerpt of text, label it as either human-written or machine-generated. We shared a dataset containing excerpts from human-written papers as well as artificially generated content and suspicious documents collected by Elsevier publishing and editorial teams. As a test set, the participants are provided with a 5x larger corpus of openly accessible human-written as well as generated papers from the same scientific domains of documents. The shared task saw 180 submissions across 14 participating teams and resulted in two published technical reports. We discuss our findings from the shared task in this overview paper.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kashnitsky-etal-2022-overview">
<titleInfo>
<title>Overview of the DAGPap22 Shared Task on Detecting Automatically Generated Scientific Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yury</namePart>
<namePart type="family">Kashnitsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Drahomira</namePart>
<namePart type="family">Herrmannova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">de Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Tsatsaronis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catriona</namePart>
<namePart type="given">Catriona</namePart>
<namePart type="family">Fennell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Labbe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Scholarly Document Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arman</namePart>
<namePart type="family">Cohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Feigenblat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</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>
<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">Kyle</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Shmueli-Scheuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">de Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucy</namePart>
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper provides an overview of the DAGPap22 shared task on the detection of automatically generated scientific papers at the Scholarly Document Process workshop colocated with COLING. We frame the detection problem as a binary classification task: given an excerpt of text, label it as either human-written or machine-generated. We shared a dataset containing excerpts from human-written papers as well as artificially generated content and suspicious documents collected by Elsevier publishing and editorial teams. As a test set, the participants are provided with a 5x larger corpus of openly accessible human-written as well as generated papers from the same scientific domains of documents. The shared task saw 180 submissions across 14 participating teams and resulted in two published technical reports. We discuss our findings from the shared task in this overview paper.</abstract>
<identifier type="citekey">kashnitsky-etal-2022-overview</identifier>
<location>
<url>https://aclanthology.org/2022.sdp-1.26</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>210</start>
<end>213</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overview of the DAGPap22 Shared Task on Detecting Automatically Generated Scientific Papers
%A Kashnitsky, Yury
%A Herrmannova, Drahomira
%A de Waard, Anita
%A Tsatsaronis, George
%A Fennell, Catriona Catriona
%A Labbe, Cyril
%Y Cohan, Arman
%Y Feigenblat, Guy
%Y Freitag, Dayne
%Y Ghosal, Tirthankar
%Y Herrmannova, Drahomira
%Y Knoth, Petr
%Y Lo, Kyle
%Y Mayr, Philipp
%Y Shmueli-Scheuer, Michal
%Y de Waard, Anita
%Y Wang, Lucy Lu
%S Proceedings of the Third Workshop on Scholarly Document Processing
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F kashnitsky-etal-2022-overview
%X This paper provides an overview of the DAGPap22 shared task on the detection of automatically generated scientific papers at the Scholarly Document Process workshop colocated with COLING. We frame the detection problem as a binary classification task: given an excerpt of text, label it as either human-written or machine-generated. We shared a dataset containing excerpts from human-written papers as well as artificially generated content and suspicious documents collected by Elsevier publishing and editorial teams. As a test set, the participants are provided with a 5x larger corpus of openly accessible human-written as well as generated papers from the same scientific domains of documents. The shared task saw 180 submissions across 14 participating teams and resulted in two published technical reports. We discuss our findings from the shared task in this overview paper.
%U https://aclanthology.org/2022.sdp-1.26
%P 210-213
Markdown (Informal)
[Overview of the DAGPap22 Shared Task on Detecting Automatically Generated Scientific Papers](https://aclanthology.org/2022.sdp-1.26) (Kashnitsky et al., sdp 2022)
ACL