@inproceedings{kuwanto-etal-2024-mitigating,
title = "Mitigating Translationese in Low-resource Languages: The Storyboard Approach",
author = "Kuwanto, Garry and
Urua, Eno-Abasi E. and
Amuok, Priscilla Amondi and
Muhammad, Shamsuddeen Hassan and
Aremu, Anuoluwapo and
Otiende, Verrah and
Nanyanga, Loice Emma and
Nyoike, Teresiah W. and
Akpan, Aniefon D. and
Udouboh, Nsima Ab and
Archibong, Idongesit Udeme and
Moses, Idara Effiong and
Ige, Ifeoluwatayo A. and
Ajibade, Benjamin and
Awokoya, Olumide Benjamin and
Abdulmumin, Idris and
Aliyu, Saminu Mohammad and
Iro, Ruqayya Nasir and
Ahmad, Ibrahim Said and
Smith, Deontae and
Michaels, Praise-EL and
Adelani, David Ifeoluwa and
Wijaya, Derry Tanti and
Andy, Anietie",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.992",
pages = "11349--11360",
abstract = "Low-resource languages often face challenges in acquiring high-quality language data due to the reliance on translation-based methods, which can introduce the translationese effect. This phenomenon results in translated sentences that lack fluency and naturalness in the target language. In this paper, we propose a novel approach for data collection by leveraging storyboards to elicit more fluent and natural sentences. Our method involves presenting native speakers with visual stimuli in the form of storyboards and collecting their descriptions without direct exposure to the source text. We conducted a comprehensive evaluation comparing our storyboard-based approach with traditional text translation-based methods in terms of accuracy and fluency. Human annotators and quantitative metrics were used to assess translation quality. The results indicate a preference for text translation in terms of accuracy, while our method demonstrates worse accuracy but better fluency in the language focused.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kuwanto-etal-2024-mitigating">
<titleInfo>
<title>Mitigating Translationese in Low-resource Languages: The Storyboard Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Garry</namePart>
<namePart type="family">Kuwanto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eno-Abasi</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Urua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priscilla</namePart>
<namePart type="given">Amondi</namePart>
<namePart type="family">Amuok</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamsuddeen</namePart>
<namePart type="given">Hassan</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuoluwapo</namePart>
<namePart type="family">Aremu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verrah</namePart>
<namePart type="family">Otiende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Loice</namePart>
<namePart type="given">Emma</namePart>
<namePart type="family">Nanyanga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teresiah</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Nyoike</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aniefon</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Akpan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nsima</namePart>
<namePart type="given">Ab</namePart>
<namePart type="family">Udouboh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Idongesit</namePart>
<namePart type="given">Udeme</namePart>
<namePart type="family">Archibong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Idara</namePart>
<namePart type="given">Effiong</namePart>
<namePart type="family">Moses</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ifeoluwatayo</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Ige</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Ajibade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olumide</namePart>
<namePart type="given">Benjamin</namePart>
<namePart type="family">Awokoya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Idris</namePart>
<namePart type="family">Abdulmumin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saminu</namePart>
<namePart type="given">Mohammad</namePart>
<namePart type="family">Aliyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruqayya</namePart>
<namePart type="given">Nasir</namePart>
<namePart type="family">Iro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="given">Said</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deontae</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Praise-EL</namePart>
<namePart type="family">Michaels</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derry</namePart>
<namePart type="given">Tanti</namePart>
<namePart type="family">Wijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anietie</namePart>
<namePart type="family">Andy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Low-resource languages often face challenges in acquiring high-quality language data due to the reliance on translation-based methods, which can introduce the translationese effect. This phenomenon results in translated sentences that lack fluency and naturalness in the target language. In this paper, we propose a novel approach for data collection by leveraging storyboards to elicit more fluent and natural sentences. Our method involves presenting native speakers with visual stimuli in the form of storyboards and collecting their descriptions without direct exposure to the source text. We conducted a comprehensive evaluation comparing our storyboard-based approach with traditional text translation-based methods in terms of accuracy and fluency. Human annotators and quantitative metrics were used to assess translation quality. The results indicate a preference for text translation in terms of accuracy, while our method demonstrates worse accuracy but better fluency in the language focused.</abstract>
<identifier type="citekey">kuwanto-etal-2024-mitigating</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.992</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11349</start>
<end>11360</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mitigating Translationese in Low-resource Languages: The Storyboard Approach
%A Kuwanto, Garry
%A Urua, Eno-Abasi E.
%A Amuok, Priscilla Amondi
%A Muhammad, Shamsuddeen Hassan
%A Aremu, Anuoluwapo
%A Otiende, Verrah
%A Nanyanga, Loice Emma
%A Nyoike, Teresiah W.
%A Akpan, Aniefon D.
%A Udouboh, Nsima Ab
%A Archibong, Idongesit Udeme
%A Moses, Idara Effiong
%A Ige, Ifeoluwatayo A.
%A Ajibade, Benjamin
%A Awokoya, Olumide Benjamin
%A Abdulmumin, Idris
%A Aliyu, Saminu Mohammad
%A Iro, Ruqayya Nasir
%A Ahmad, Ibrahim Said
%A Smith, Deontae
%A Michaels, Praise-EL
%A Adelani, David Ifeoluwa
%A Wijaya, Derry Tanti
%A Andy, Anietie
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F kuwanto-etal-2024-mitigating
%X Low-resource languages often face challenges in acquiring high-quality language data due to the reliance on translation-based methods, which can introduce the translationese effect. This phenomenon results in translated sentences that lack fluency and naturalness in the target language. In this paper, we propose a novel approach for data collection by leveraging storyboards to elicit more fluent and natural sentences. Our method involves presenting native speakers with visual stimuli in the form of storyboards and collecting their descriptions without direct exposure to the source text. We conducted a comprehensive evaluation comparing our storyboard-based approach with traditional text translation-based methods in terms of accuracy and fluency. Human annotators and quantitative metrics were used to assess translation quality. The results indicate a preference for text translation in terms of accuracy, while our method demonstrates worse accuracy but better fluency in the language focused.
%U https://aclanthology.org/2024.lrec-main.992
%P 11349-11360
Markdown (Informal)
[Mitigating Translationese in Low-resource Languages: The Storyboard Approach](https://aclanthology.org/2024.lrec-main.992) (Kuwanto et al., LREC-COLING 2024)
ACL
- Garry Kuwanto, Eno-Abasi E. Urua, Priscilla Amondi Amuok, Shamsuddeen Hassan Muhammad, Anuoluwapo Aremu, Verrah Otiende, Loice Emma Nanyanga, Teresiah W. Nyoike, Aniefon D. Akpan, Nsima Ab Udouboh, Idongesit Udeme Archibong, Idara Effiong Moses, Ifeoluwatayo A. Ige, Benjamin Ajibade, Olumide Benjamin Awokoya, Idris Abdulmumin, Saminu Mohammad Aliyu, Ruqayya Nasir Iro, Ibrahim Said Ahmad, et al.. 2024. Mitigating Translationese in Low-resource Languages: The Storyboard Approach. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11349–11360, Torino, Italia. ELRA and ICCL.