@inproceedings{popovic-etal-2024-effects,
title = "Effects of different types of noise in user-generated reviews on human and machine translations including {C}hat{GPT}",
author = "Popovic, Maja and
Lapshinova-Koltunski, Ekaterina and
Koponen, Maarit",
editor = {van der Goot, Rob and
Bak, JinYeong and
M{\"u}ller-Eberstein, Max and
Xu, Wei and
Ritter, Alan and
Baldwin, Tim},
booktitle = "Proceedings of the Ninth Workshop on Noisy and User-generated Text (W-NUT 2024)",
month = mar,
year = "2024",
address = "San {\.G}iljan, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wnut-1.3",
pages = "17--30",
abstract = "This paper investigates effects of noisy source texts (containing spelling and grammar errors, informal words or expressions, etc.) on human and machine translations, namely whether the noisy phenomena are kept in the translations, corrected, or caused errors. The analysed data consists of English user reviews of Amazon products translated into Croatian, Russian and Finnish by professional translators, translation students, machine translation (MT) systems, and ChatGPT language model. The results show that overall, ChatGPT and professional translators mostly correct/standardise those parts, while students are often keeping them. Furthermore, MT systems are most prone to errors while ChatGPT is more robust, but notably less robust than human translators. Finally, some of the phenomena are particularly challenging both for MT systems and for ChatGPT, especially spelling errors and informal constructions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="popovic-etal-2024-effects">
<titleInfo>
<title>Effects of different types of noise in user-generated reviews on human and machine translations including ChatGPT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Lapshinova-Koltunski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Workshop on Noisy and User-generated Text (W-NUT 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">van der Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">JinYeong</namePart>
<namePart type="family">Bak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Müller-Eberstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Ġiljan, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper investigates effects of noisy source texts (containing spelling and grammar errors, informal words or expressions, etc.) on human and machine translations, namely whether the noisy phenomena are kept in the translations, corrected, or caused errors. The analysed data consists of English user reviews of Amazon products translated into Croatian, Russian and Finnish by professional translators, translation students, machine translation (MT) systems, and ChatGPT language model. The results show that overall, ChatGPT and professional translators mostly correct/standardise those parts, while students are often keeping them. Furthermore, MT systems are most prone to errors while ChatGPT is more robust, but notably less robust than human translators. Finally, some of the phenomena are particularly challenging both for MT systems and for ChatGPT, especially spelling errors and informal constructions.</abstract>
<identifier type="citekey">popovic-etal-2024-effects</identifier>
<location>
<url>https://aclanthology.org/2024.wnut-1.3</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>17</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effects of different types of noise in user-generated reviews on human and machine translations including ChatGPT
%A Popovic, Maja
%A Lapshinova-Koltunski, Ekaterina
%A Koponen, Maarit
%Y van der Goot, Rob
%Y Bak, JinYeong
%Y Müller-Eberstein, Max
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%S Proceedings of the Ninth Workshop on Noisy and User-generated Text (W-NUT 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C San Ġiljan, Malta
%F popovic-etal-2024-effects
%X This paper investigates effects of noisy source texts (containing spelling and grammar errors, informal words or expressions, etc.) on human and machine translations, namely whether the noisy phenomena are kept in the translations, corrected, or caused errors. The analysed data consists of English user reviews of Amazon products translated into Croatian, Russian and Finnish by professional translators, translation students, machine translation (MT) systems, and ChatGPT language model. The results show that overall, ChatGPT and professional translators mostly correct/standardise those parts, while students are often keeping them. Furthermore, MT systems are most prone to errors while ChatGPT is more robust, but notably less robust than human translators. Finally, some of the phenomena are particularly challenging both for MT systems and for ChatGPT, especially spelling errors and informal constructions.
%U https://aclanthology.org/2024.wnut-1.3
%P 17-30
Markdown (Informal)
[Effects of different types of noise in user-generated reviews on human and machine translations including ChatGPT](https://aclanthology.org/2024.wnut-1.3) (Popovic et al., WNUT-WS 2024)
ACL