@inproceedings{lay-etal-2022-investigating,
title = "Investigating the detection of Tortured Phrases in Scientific Literature",
author = "Lay, Puthineath and
Lentschat, Martin 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-1.4",
pages = "32--36",
abstract = "With the help of online tools, unscrupulous authors can today generate a pseudo-scientific article and attempt to publish it. Some of these tools work by replacing or paraphrasing existing texts to produce new content, but they have a tendency to generate nonsensical expressions. A recent study introduced the concept of {``}tortured phrase{''}, an unexpected odd phrase that appears instead of the fixed expression. E.g. counterfeit consciousness instead of artificial intelligence. The present study aims at investigating how tortured phrases, that are not yet listed, can be detected automatically. We conducted several experiments, including non-neural binary classification, neural binary classification and cosine similarity comparison of the phrase tokens, yielding noticeable results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lay-etal-2022-investigating">
<titleInfo>
<title>Investigating the detection of Tortured Phrases in Scientific Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Puthineath</namePart>
<namePart type="family">Lay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Lentschat</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>With the help of online tools, unscrupulous authors can today generate a pseudo-scientific article and attempt to publish it. Some of these tools work by replacing or paraphrasing existing texts to produce new content, but they have a tendency to generate nonsensical expressions. A recent study introduced the concept of “tortured phrase”, an unexpected odd phrase that appears instead of the fixed expression. E.g. counterfeit consciousness instead of artificial intelligence. The present study aims at investigating how tortured phrases, that are not yet listed, can be detected automatically. We conducted several experiments, including non-neural binary classification, neural binary classification and cosine similarity comparison of the phrase tokens, yielding noticeable results.</abstract>
<identifier type="citekey">lay-etal-2022-investigating</identifier>
<location>
<url>https://aclanthology.org/2022.sdp-1.4</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>32</start>
<end>36</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating the detection of Tortured Phrases in Scientific Literature
%A Lay, Puthineath
%A Lentschat, Martin
%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 lay-etal-2022-investigating
%X With the help of online tools, unscrupulous authors can today generate a pseudo-scientific article and attempt to publish it. Some of these tools work by replacing or paraphrasing existing texts to produce new content, but they have a tendency to generate nonsensical expressions. A recent study introduced the concept of “tortured phrase”, an unexpected odd phrase that appears instead of the fixed expression. E.g. counterfeit consciousness instead of artificial intelligence. The present study aims at investigating how tortured phrases, that are not yet listed, can be detected automatically. We conducted several experiments, including non-neural binary classification, neural binary classification and cosine similarity comparison of the phrase tokens, yielding noticeable results.
%U https://aclanthology.org/2022.sdp-1.4
%P 32-36
Markdown (Informal)
[Investigating the detection of Tortured Phrases in Scientific Literature](https://aclanthology.org/2022.sdp-1.4) (Lay et al., sdp 2022)
ACL