@inproceedings{wang-etal-2024-document,
title = "Document Alignment based on Overlapping Fixed-Length Segments",
author = "Wang, Xiaotian and
Utsuro, Takehito and
Nagata, Masaaki",
editor = "Fu, Xiyan and
Fleisig, Eve",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-srw.10",
pages = "103--113",
abstract = "Acquiring large-scale parallel corpora is crucial for NLP tasks such asNeural Machine Translation, and web crawling has become a popularmethodology for this purpose. Previous studies have been conductedbased on sentence-based segmentation (SBS) when aligning documents invarious languages which are obtained through web crawling. Among them,the TK-PERT method (Thompson and Koehn, 2020) achieved state-of-the-artresults and addressed the boilerplate text in web crawling data wellthrough a down-weighting approach. However, there remains a problemwith how to handle long-text encoding better. Thus, we introduce thestrategy of Overlapping Fixed-Length Segmentation (OFLS) in place ofSBS, and observe a pronounced enhancement when performing the sameapproach for document alignment. In this paper, we compare the SBS andOFLS using three previous methods, Mean-Pool, TK-PERT (Thompson andKoehn, 2020), and Optimal Transport (Clark et al., 2019; El- Kishky andGuzman, 2020), on the WMT16 document alignment shared task forFrench-English, as well as on our self-established Japanese-Englishdataset MnRN. As a result, for the WMT16 task, various SBS basedmethods showed an increase in recall by 1{\%} to 10{\%} after reproductionwith OFLS. For MnRN data, OFLS demonstrated notable accuracyimprovements and exhibited faster document embedding speed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-document">
<titleInfo>
<title>Document Alignment based on Overlapping Fixed-Length Segments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaotian</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takehito</namePart>
<namePart type="family">Utsuro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</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>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiyan</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eve</namePart>
<namePart type="family">Fleisig</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>Acquiring large-scale parallel corpora is crucial for NLP tasks such asNeural Machine Translation, and web crawling has become a popularmethodology for this purpose. Previous studies have been conductedbased on sentence-based segmentation (SBS) when aligning documents invarious languages which are obtained through web crawling. Among them,the TK-PERT method (Thompson and Koehn, 2020) achieved state-of-the-artresults and addressed the boilerplate text in web crawling data wellthrough a down-weighting approach. However, there remains a problemwith how to handle long-text encoding better. Thus, we introduce thestrategy of Overlapping Fixed-Length Segmentation (OFLS) in place ofSBS, and observe a pronounced enhancement when performing the sameapproach for document alignment. In this paper, we compare the SBS andOFLS using three previous methods, Mean-Pool, TK-PERT (Thompson andKoehn, 2020), and Optimal Transport (Clark et al., 2019; El- Kishky andGuzman, 2020), on the WMT16 document alignment shared task forFrench-English, as well as on our self-established Japanese-Englishdataset MnRN. As a result, for the WMT16 task, various SBS basedmethods showed an increase in recall by 1% to 10% after reproductionwith OFLS. For MnRN data, OFLS demonstrated notable accuracyimprovements and exhibited faster document embedding speed.</abstract>
<identifier type="citekey">wang-etal-2024-document</identifier>
<location>
<url>https://aclanthology.org/2024.acl-srw.10</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>103</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Document Alignment based on Overlapping Fixed-Length Segments
%A Wang, Xiaotian
%A Utsuro, Takehito
%A Nagata, Masaaki
%Y Fu, Xiyan
%Y Fleisig, Eve
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wang-etal-2024-document
%X Acquiring large-scale parallel corpora is crucial for NLP tasks such asNeural Machine Translation, and web crawling has become a popularmethodology for this purpose. Previous studies have been conductedbased on sentence-based segmentation (SBS) when aligning documents invarious languages which are obtained through web crawling. Among them,the TK-PERT method (Thompson and Koehn, 2020) achieved state-of-the-artresults and addressed the boilerplate text in web crawling data wellthrough a down-weighting approach. However, there remains a problemwith how to handle long-text encoding better. Thus, we introduce thestrategy of Overlapping Fixed-Length Segmentation (OFLS) in place ofSBS, and observe a pronounced enhancement when performing the sameapproach for document alignment. In this paper, we compare the SBS andOFLS using three previous methods, Mean-Pool, TK-PERT (Thompson andKoehn, 2020), and Optimal Transport (Clark et al., 2019; El- Kishky andGuzman, 2020), on the WMT16 document alignment shared task forFrench-English, as well as on our self-established Japanese-Englishdataset MnRN. As a result, for the WMT16 task, various SBS basedmethods showed an increase in recall by 1% to 10% after reproductionwith OFLS. For MnRN data, OFLS demonstrated notable accuracyimprovements and exhibited faster document embedding speed.
%U https://aclanthology.org/2024.acl-srw.10
%P 103-113
Markdown (Informal)
[Document Alignment based on Overlapping Fixed-Length Segments](https://aclanthology.org/2024.acl-srw.10) (Wang et al., ACL 2024)
ACL
- Xiaotian Wang, Takehito Utsuro, and Masaaki Nagata. 2024. Document Alignment based on Overlapping Fixed-Length Segments. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 103–113, Bangkok, Thailand. Association for Computational Linguistics.