@inproceedings{park-etal-2024-translation,
title = "Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering",
author = "Park, ChaeHun and
Lee, Koanho and
Lim, Hyesu and
Kim, Jaeseok and
Park, Junmo and
Heo, Yu-Jung and
Chang, Du-Seong and
Choo, Jaegul",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.308",
doi = "10.18653/v1/2024.findings-acl.308",
pages = "5193--5221",
abstract = "Building a reliable visual question answering (VQA) system across different languages is a challenging problem, primarily due to the lack of abundant samples for training. To address this challenge, recent studies have employed machine translation systems for the cross-lingual VQA task. This involves translating the evaluation samples into a source language (usually English) and using monolingual models (i.e., translate-test). However, our analysis reveals that translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. We find that these artifacts can significantly affect the models, confirmed by extensive experiments across diverse models, languages, and translation processes. In light of this, we present a simple data augmentation strategy that can alleviate the adverse impacts of translation artifacts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2024-translation">
<titleInfo>
<title>Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">ChaeHun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koanho</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyesu</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaeseok</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junmo</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Jung</namePart>
<namePart type="family">Heo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Du-Seong</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaegul</namePart>
<namePart type="family">Choo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building a reliable visual question answering (VQA) system across different languages is a challenging problem, primarily due to the lack of abundant samples for training. To address this challenge, recent studies have employed machine translation systems for the cross-lingual VQA task. This involves translating the evaluation samples into a source language (usually English) and using monolingual models (i.e., translate-test). However, our analysis reveals that translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. We find that these artifacts can significantly affect the models, confirmed by extensive experiments across diverse models, languages, and translation processes. In light of this, we present a simple data augmentation strategy that can alleviate the adverse impacts of translation artifacts.</abstract>
<identifier type="citekey">park-etal-2024-translation</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.308</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.308</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>5193</start>
<end>5221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering
%A Park, ChaeHun
%A Lee, Koanho
%A Lim, Hyesu
%A Kim, Jaeseok
%A Park, Junmo
%A Heo, Yu-Jung
%A Chang, Du-Seong
%A Choo, Jaegul
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F park-etal-2024-translation
%X Building a reliable visual question answering (VQA) system across different languages is a challenging problem, primarily due to the lack of abundant samples for training. To address this challenge, recent studies have employed machine translation systems for the cross-lingual VQA task. This involves translating the evaluation samples into a source language (usually English) and using monolingual models (i.e., translate-test). However, our analysis reveals that translated texts contain unique characteristics distinct from human-written ones, referred to as translation artifacts. We find that these artifacts can significantly affect the models, confirmed by extensive experiments across diverse models, languages, and translation processes. In light of this, we present a simple data augmentation strategy that can alleviate the adverse impacts of translation artifacts.
%R 10.18653/v1/2024.findings-acl.308
%U https://aclanthology.org/2024.findings-acl.308
%U https://doi.org/10.18653/v1/2024.findings-acl.308
%P 5193-5221
Markdown (Informal)
[Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering](https://aclanthology.org/2024.findings-acl.308) (Park et al., Findings 2024)
ACL
- ChaeHun Park, Koanho Lee, Hyesu Lim, Jaeseok Kim, Junmo Park, Yu-Jung Heo, Du-Seong Chang, and Jaegul Choo. 2024. Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering. In Findings of the Association for Computational Linguistics: ACL 2024, pages 5193–5221, Bangkok, Thailand. Association for Computational Linguistics.