@inproceedings{jiang-etal-2026-parallel,
title = "Parallel Sentence Filtering for Low-Resource Language Pairs: A Case Study for {U}pper {S}orbian, {G}erman, and {C}zech",
author = "Jiang, Ruiyang and
Okabe, Shu and
Fraser, Alexander",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.699/",
doi = "10.63317/2ym7m4jx58jj",
pages = "8883--8896",
abstract = "As parallel corpora for low-resource languages are scarce, and automatic approaches to mine sentence pairs can lead to noisy datasets, parallel sentence filtering aims to detect only actual translations. We study here two language pairs: Upper Sorbian{--}German and Czech{--}German to represent both high and low availability of data resources. To evaluate filtering performance, we generate synthetic datasets by combining existing parallel corpora with synthetic non-parallel pairs, notably with five types of local semantic changes on the German side, such as negation or modality transformations. We represent sentences using three multilingual language models, XLM-R, Glot500m, and LaBSE, and train classifiers for the task. All three model representations led to worse filtering quality when pairs were altered more subtly, such as an antonym replacement. We still observed that a language model pre-trained on the considered language achieves more robust classification performance when sentence pairs are more ambiguous. We also evaluated a cross-lingual approach where the classifier is trained on the Czech{--}German pair and then applied to the Upper Sorbian{--}German pair. Such a language transfer paves the way for filtering other low-resource language pairs in the future."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2026-parallel">
<titleInfo>
<title>Parallel Sentence Filtering for Low-Resource Language Pairs: A Case Study for Upper Sorbian, German, and Czech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruiyang</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shu</namePart>
<namePart type="family">Okabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As parallel corpora for low-resource languages are scarce, and automatic approaches to mine sentence pairs can lead to noisy datasets, parallel sentence filtering aims to detect only actual translations. We study here two language pairs: Upper Sorbian–German and Czech–German to represent both high and low availability of data resources. To evaluate filtering performance, we generate synthetic datasets by combining existing parallel corpora with synthetic non-parallel pairs, notably with five types of local semantic changes on the German side, such as negation or modality transformations. We represent sentences using three multilingual language models, XLM-R, Glot500m, and LaBSE, and train classifiers for the task. All three model representations led to worse filtering quality when pairs were altered more subtly, such as an antonym replacement. We still observed that a language model pre-trained on the considered language achieves more robust classification performance when sentence pairs are more ambiguous. We also evaluated a cross-lingual approach where the classifier is trained on the Czech–German pair and then applied to the Upper Sorbian–German pair. Such a language transfer paves the way for filtering other low-resource language pairs in the future.</abstract>
<identifier type="citekey">jiang-etal-2026-parallel</identifier>
<identifier type="doi">10.63317/2ym7m4jx58jj</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.699/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>8883</start>
<end>8896</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parallel Sentence Filtering for Low-Resource Language Pairs: A Case Study for Upper Sorbian, German, and Czech
%A Jiang, Ruiyang
%A Okabe, Shu
%A Fraser, Alexander
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F jiang-etal-2026-parallel
%X As parallel corpora for low-resource languages are scarce, and automatic approaches to mine sentence pairs can lead to noisy datasets, parallel sentence filtering aims to detect only actual translations. We study here two language pairs: Upper Sorbian–German and Czech–German to represent both high and low availability of data resources. To evaluate filtering performance, we generate synthetic datasets by combining existing parallel corpora with synthetic non-parallel pairs, notably with five types of local semantic changes on the German side, such as negation or modality transformations. We represent sentences using three multilingual language models, XLM-R, Glot500m, and LaBSE, and train classifiers for the task. All three model representations led to worse filtering quality when pairs were altered more subtly, such as an antonym replacement. We still observed that a language model pre-trained on the considered language achieves more robust classification performance when sentence pairs are more ambiguous. We also evaluated a cross-lingual approach where the classifier is trained on the Czech–German pair and then applied to the Upper Sorbian–German pair. Such a language transfer paves the way for filtering other low-resource language pairs in the future.
%R 10.63317/2ym7m4jx58jj
%U https://aclanthology.org/2026.lrec-1.699/
%U https://doi.org/10.63317/2ym7m4jx58jj
%P 8883-8896
Markdown (Informal)
[Parallel Sentence Filtering for Low-Resource Language Pairs: A Case Study for Upper Sorbian, German, and Czech](https://aclanthology.org/2026.lrec-1.699/) (Jiang et al., LREC 2026)
ACL