@inproceedings{ja-rgensen-mengshoel-2025-cross,
title = "Cross-Lingual Sentence Compression for Length-Constrained Subtitles in Low-Resource Settings",
author = "J{\~A}, rgensen, Tollef Emil and
Mengshoel, Ole Jakob",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.429/",
pages = "6447--6458",
abstract = "This paper explores the joint task of machine translation and sentence compression, emphasizing its application in subtitle generation for broadcast and live media for low-resource languages and hardware. We develop CLSC (Cross-Lingual Sentence Compression), a system trained on openly available parallel corpora organized by compression ratios, where the target length is constrained to a fraction of the source sentence length. We present two training methods: 1) Multiple Models (MM), where individual models are trained separately for each compression ratio, and 2) a Controllable Model (CM), a single model per language using a compression token to encode length constraints. We evaluate both subtitle data and transcriptions from the EuroParl corpus. To accommodate low-resource settings, we constrain data sampling for training and show results for transcriptions in French, Hungarian, Lithuanian, and Polish and subtitles in Albanian, Basque, Malay, and Norwegian. Our models preserve high semantic meaning and metric evaluations for compressed contexts."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ja-rgensen-mengshoel-2025-cross">
<titleInfo>
<title>Cross-Lingual Sentence Compression for Length-Constrained Subtitles in Low-Resource Settings</title>
</titleInfo>
<name type="personal">
<namePart type="given">rgensen,</namePart>
<namePart type="given">Tollef</namePart>
<namePart type="given">Emil</namePart>
<namePart type="family">JÃ</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ole</namePart>
<namePart type="given">Jakob</namePart>
<namePart type="family">Mengshoel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper explores the joint task of machine translation and sentence compression, emphasizing its application in subtitle generation for broadcast and live media for low-resource languages and hardware. We develop CLSC (Cross-Lingual Sentence Compression), a system trained on openly available parallel corpora organized by compression ratios, where the target length is constrained to a fraction of the source sentence length. We present two training methods: 1) Multiple Models (MM), where individual models are trained separately for each compression ratio, and 2) a Controllable Model (CM), a single model per language using a compression token to encode length constraints. We evaluate both subtitle data and transcriptions from the EuroParl corpus. To accommodate low-resource settings, we constrain data sampling for training and show results for transcriptions in French, Hungarian, Lithuanian, and Polish and subtitles in Albanian, Basque, Malay, and Norwegian. Our models preserve high semantic meaning and metric evaluations for compressed contexts.</abstract>
<identifier type="citekey">ja-rgensen-mengshoel-2025-cross</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.429/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>6447</start>
<end>6458</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual Sentence Compression for Length-Constrained Subtitles in Low-Resource Settings
%A JÃ, rgensen, Tollef Emil
%A Mengshoel, Ole Jakob
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F ja-rgensen-mengshoel-2025-cross
%X This paper explores the joint task of machine translation and sentence compression, emphasizing its application in subtitle generation for broadcast and live media for low-resource languages and hardware. We develop CLSC (Cross-Lingual Sentence Compression), a system trained on openly available parallel corpora organized by compression ratios, where the target length is constrained to a fraction of the source sentence length. We present two training methods: 1) Multiple Models (MM), where individual models are trained separately for each compression ratio, and 2) a Controllable Model (CM), a single model per language using a compression token to encode length constraints. We evaluate both subtitle data and transcriptions from the EuroParl corpus. To accommodate low-resource settings, we constrain data sampling for training and show results for transcriptions in French, Hungarian, Lithuanian, and Polish and subtitles in Albanian, Basque, Malay, and Norwegian. Our models preserve high semantic meaning and metric evaluations for compressed contexts.
%U https://aclanthology.org/2025.coling-main.429/
%P 6447-6458
Markdown (Informal)
[Cross-Lingual Sentence Compression for Length-Constrained Subtitles in Low-Resource Settings](https://aclanthology.org/2025.coling-main.429/) (JÃ, rgensen & Mengshoel, COLING 2025)
ACL