@inproceedings{nguyen-son-etal-2021-machine,
title = "Machine Translated Text Detection Through Text Similarity with Round-Trip Translation",
author = "Nguyen-Son, Hoang-Quoc and
Thao, Tran and
Hidano, Seira and
Gupta, Ishita and
Kiyomoto, Shinsaku",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.462",
doi = "10.18653/v1/2021.naacl-main.462",
pages = "5792--5797",
abstract = "Translated texts have been used for malicious purposes, i.e., plagiarism or fake reviews. Existing detectors have been built around a specific translator (e.g., Google) but fail to detect a translated text from a strange translator. If we use the same translator, the translated text is similar to its round-trip translation, which is when text is translated into another language and translated back into the original language. However, a round-trip translated text is significantly different from the original text or a translated text using a strange translator. Hence, we propose a detector using text similarity with round-trip translation (TSRT). TSRT achieves 86.9{\%} accuracy in detecting a translated text from a strange translator. It outperforms existing detectors (77.9{\%}) and human recognition (53.3{\%}).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-son-etal-2021-machine">
<titleInfo>
<title>Machine Translated Text Detection Through Text Similarity with Round-Trip Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hoang-Quoc</namePart>
<namePart type="family">Nguyen-Son</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tran</namePart>
<namePart type="family">Thao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seira</namePart>
<namePart type="family">Hidano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ishita</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinsaku</namePart>
<namePart type="family">Kiyomoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Translated texts have been used for malicious purposes, i.e., plagiarism or fake reviews. Existing detectors have been built around a specific translator (e.g., Google) but fail to detect a translated text from a strange translator. If we use the same translator, the translated text is similar to its round-trip translation, which is when text is translated into another language and translated back into the original language. However, a round-trip translated text is significantly different from the original text or a translated text using a strange translator. Hence, we propose a detector using text similarity with round-trip translation (TSRT). TSRT achieves 86.9% accuracy in detecting a translated text from a strange translator. It outperforms existing detectors (77.9%) and human recognition (53.3%).</abstract>
<identifier type="citekey">nguyen-son-etal-2021-machine</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.462</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.462</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5792</start>
<end>5797</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Translated Text Detection Through Text Similarity with Round-Trip Translation
%A Nguyen-Son, Hoang-Quoc
%A Thao, Tran
%A Hidano, Seira
%A Gupta, Ishita
%A Kiyomoto, Shinsaku
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F nguyen-son-etal-2021-machine
%X Translated texts have been used for malicious purposes, i.e., plagiarism or fake reviews. Existing detectors have been built around a specific translator (e.g., Google) but fail to detect a translated text from a strange translator. If we use the same translator, the translated text is similar to its round-trip translation, which is when text is translated into another language and translated back into the original language. However, a round-trip translated text is significantly different from the original text or a translated text using a strange translator. Hence, we propose a detector using text similarity with round-trip translation (TSRT). TSRT achieves 86.9% accuracy in detecting a translated text from a strange translator. It outperforms existing detectors (77.9%) and human recognition (53.3%).
%R 10.18653/v1/2021.naacl-main.462
%U https://aclanthology.org/2021.naacl-main.462
%U https://doi.org/10.18653/v1/2021.naacl-main.462
%P 5792-5797
Markdown (Informal)
[Machine Translated Text Detection Through Text Similarity with Round-Trip Translation](https://aclanthology.org/2021.naacl-main.462) (Nguyen-Son et al., NAACL 2021)
ACL