@inproceedings{minh-cong-etal-2023-fast,
title = "A Fast Method to Filter Noisy Parallel Data {WMT}2023 Shared Task on Parallel Data Curation",
author = "Minh-Cong, Nguyen-Hoang and
Vinh, Nguyen Van and
Le-Minh, Nguyen",
editor = "Koehn, Philipp and
Haddow, Barry and
Kocmi, Tom and
Monz, Christof",
booktitle = "Proceedings of the Eighth Conference on Machine Translation",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wmt-1.37",
doi = "10.18653/v1/2023.wmt-1.37",
pages = "359--365",
abstract = "The effectiveness of a machine translation (MT) system is intricately linked to the quality of its training dataset. In an era where websites offer an extensive repository of translations such as movie subtitles, stories, and TED Talks, the fundamental challenge resides in pinpointing the sentence pairs or documents that represent accurate translations of each other. This paper presents the results of our submission to the shared task WMT2023 (Sloto et al., 2023), which aimed to evaluate parallel data curation methods for improving the MT system. The task involved alignment and filtering data to create high-quality parallel corpora for training and evaluating the MT models. Our approach leveraged a combination of dictionary and rule-based methods to ensure data quality and consistency. We achieved an improvement with the highest 1.6 BLEU score compared to the baseline system. Significantly, our approach showed consistent improvements across all test sets, suggesting its efficiency.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="minh-cong-etal-2023-fast">
<titleInfo>
<title>A Fast Method to Filter Noisy Parallel Data WMT2023 Shared Task on Parallel Data Curation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nguyen-Hoang</namePart>
<namePart type="family">Minh-Cong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="given">Van</namePart>
<namePart type="family">Vinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="family">Le-Minh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The effectiveness of a machine translation (MT) system is intricately linked to the quality of its training dataset. In an era where websites offer an extensive repository of translations such as movie subtitles, stories, and TED Talks, the fundamental challenge resides in pinpointing the sentence pairs or documents that represent accurate translations of each other. This paper presents the results of our submission to the shared task WMT2023 (Sloto et al., 2023), which aimed to evaluate parallel data curation methods for improving the MT system. The task involved alignment and filtering data to create high-quality parallel corpora for training and evaluating the MT models. Our approach leveraged a combination of dictionary and rule-based methods to ensure data quality and consistency. We achieved an improvement with the highest 1.6 BLEU score compared to the baseline system. Significantly, our approach showed consistent improvements across all test sets, suggesting its efficiency.</abstract>
<identifier type="citekey">minh-cong-etal-2023-fast</identifier>
<identifier type="doi">10.18653/v1/2023.wmt-1.37</identifier>
<location>
<url>https://aclanthology.org/2023.wmt-1.37</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>359</start>
<end>365</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Fast Method to Filter Noisy Parallel Data WMT2023 Shared Task on Parallel Data Curation
%A Minh-Cong, Nguyen-Hoang
%A Vinh, Nguyen Van
%A Le-Minh, Nguyen
%Y Koehn, Philipp
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Monz, Christof
%S Proceedings of the Eighth Conference on Machine Translation
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F minh-cong-etal-2023-fast
%X The effectiveness of a machine translation (MT) system is intricately linked to the quality of its training dataset. In an era where websites offer an extensive repository of translations such as movie subtitles, stories, and TED Talks, the fundamental challenge resides in pinpointing the sentence pairs or documents that represent accurate translations of each other. This paper presents the results of our submission to the shared task WMT2023 (Sloto et al., 2023), which aimed to evaluate parallel data curation methods for improving the MT system. The task involved alignment and filtering data to create high-quality parallel corpora for training and evaluating the MT models. Our approach leveraged a combination of dictionary and rule-based methods to ensure data quality and consistency. We achieved an improvement with the highest 1.6 BLEU score compared to the baseline system. Significantly, our approach showed consistent improvements across all test sets, suggesting its efficiency.
%R 10.18653/v1/2023.wmt-1.37
%U https://aclanthology.org/2023.wmt-1.37
%U https://doi.org/10.18653/v1/2023.wmt-1.37
%P 359-365
Markdown (Informal)
[A Fast Method to Filter Noisy Parallel Data WMT2023 Shared Task on Parallel Data Curation](https://aclanthology.org/2023.wmt-1.37) (Minh-Cong et al., WMT 2023)
ACL