@inproceedings{ozer-etal-2026-interlinear,
title = "Interlinear Glosses as a Multilingual Pivot for Machine Translation: An Updated Study on {T}urkish with Restricted Resources",
author = "Ozer, Volkan and
Okabe, Shu and
Fraser, Alexander",
editor = "Ojha, Atul Kr. and
Sakti, Sakriani and
Soria, Claudia and
Melero, Maite and
McCrae, John P. and
Lignos, Constantine and
Liu, Chao-Hong and
Claramunt, German Rigau and
Rehm, Georg",
booktitle = "Proceedings of the {SIGUL} 2026 Joint Workshop with {ELE}, {EURALI}, and {DCLRL}: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.sigul-1.19/",
doi = "10.63317/4km7f5p8epxt",
pages = "183--197",
abstract = "Translating very low-resource languages is a challenge that has been approached using available linguistic cues. Among them, interlinear glosses are linguistic annotations that can essentially bridge the gap between two languages thanks to both grammatical and lexical information. We perform a case study on a simulated low-resource condition for Turkish, a morphologically rich language, with a pipeline approach, following (Zhou et al., 2020). A source sentence is passed through a morphological analyzer and a bilingual dictionary to obtain a gloss-like representation. We then evaluate the current capacity of Neural Machine Translation systems and Large Language Models in performing the translation task from interlinear glosses into fluent English translations. We notably evaluate how performance scales with multilingual glossed data and how translation is affected by pseudo-glosses. Pivoting with glosses remains a better approach than a direct translation for languages with limited parallel data for training. Although glosses remain helpful resources, translations are sensitive to their quality, especially for lexical information."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ozer-etal-2026-interlinear">
<titleInfo>
<title>Interlinear Glosses as a Multilingual Pivot for Machine Translation: An Updated Study on Turkish with Restricted Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Volkan</namePart>
<namePart type="family">Ozer</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 SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</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">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Translating very low-resource languages is a challenge that has been approached using available linguistic cues. Among them, interlinear glosses are linguistic annotations that can essentially bridge the gap between two languages thanks to both grammatical and lexical information. We perform a case study on a simulated low-resource condition for Turkish, a morphologically rich language, with a pipeline approach, following (Zhou et al., 2020). A source sentence is passed through a morphological analyzer and a bilingual dictionary to obtain a gloss-like representation. We then evaluate the current capacity of Neural Machine Translation systems and Large Language Models in performing the translation task from interlinear glosses into fluent English translations. We notably evaluate how performance scales with multilingual glossed data and how translation is affected by pseudo-glosses. Pivoting with glosses remains a better approach than a direct translation for languages with limited parallel data for training. Although glosses remain helpful resources, translations are sensitive to their quality, especially for lexical information.</abstract>
<identifier type="citekey">ozer-etal-2026-interlinear</identifier>
<identifier type="doi">10.63317/4km7f5p8epxt</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.19/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>183</start>
<end>197</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interlinear Glosses as a Multilingual Pivot for Machine Translation: An Updated Study on Turkish with Restricted Resources
%A Ozer, Volkan
%A Okabe, Shu
%A Fraser, Alexander
%Y Ojha, Atul Kr.
%Y Sakti, Sakriani
%Y Soria, Claudia
%Y Melero, Maite
%Y McCrae, John P.
%Y Lignos, Constantine
%Y Liu, Chao-Hong
%Y Claramunt, German Rigau
%Y Rehm, Georg
%S Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F ozer-etal-2026-interlinear
%X Translating very low-resource languages is a challenge that has been approached using available linguistic cues. Among them, interlinear glosses are linguistic annotations that can essentially bridge the gap between two languages thanks to both grammatical and lexical information. We perform a case study on a simulated low-resource condition for Turkish, a morphologically rich language, with a pipeline approach, following (Zhou et al., 2020). A source sentence is passed through a morphological analyzer and a bilingual dictionary to obtain a gloss-like representation. We then evaluate the current capacity of Neural Machine Translation systems and Large Language Models in performing the translation task from interlinear glosses into fluent English translations. We notably evaluate how performance scales with multilingual glossed data and how translation is affected by pseudo-glosses. Pivoting with glosses remains a better approach than a direct translation for languages with limited parallel data for training. Although glosses remain helpful resources, translations are sensitive to their quality, especially for lexical information.
%R 10.63317/4km7f5p8epxt
%U https://aclanthology.org/2026.sigul-1.19/
%U https://doi.org/10.63317/4km7f5p8epxt
%P 183-197
Markdown (Informal)
[Interlinear Glosses as a Multilingual Pivot for Machine Translation: An Updated Study on Turkish with Restricted Resources](https://aclanthology.org/2026.sigul-1.19/) (Ozer et al., SIGUL-EURALI-DCLRL 2026)
ACL