@inproceedings{frontull-etal-2026-adding,
title = {Adding ciofs and ci{\"u}fs to {BOUQ}u{ET}: Benchmark Extension to {L}adin},
author = "Frontull, Samuel and
Castlunger, Lara and
Oberhollenzer, Maximilian and
Comploj, Karin and
Videsott, Ruth and
Sama, Robert and
Perathoner, Gabriel and
Zoli, Carlo and
Videsott, Paul",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Eleventh Conference on Machine Translation",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wmt-main.194/",
pages = "2493--2504",
ISBN = "979-8-89176-474-3",
abstract = {Benchmarks do more than report scores: they provide a shared basis for evaluating methods, comparing systems, and measuring progress. As language technologies are now widely integrated into everyday life, efforts should also be made to include minority languages in the resources that underpin language-technology development. If languages are absent from relevant benchmarks, they remain harder to evaluate, compare, and incorporate into future language technologies. Expanding benchmark coverage is therefore essential for ensuring fair evaluation, increasing visibility, and enabling continued development of language technologies for these communities. To support MT development for Ladin, we contribute a Ladin extension of BOUQuET to the WMT 2026 OLDI shared task, covering the Val Badia and Gherd{\"e}ina varieties. We present a systematic reference-creation workflow combining human translation, expert revision, cross-variant alignment, and blind ranking to produce high-quality references. The dataset is released under the CC BY-SA 4.0 license.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="frontull-etal-2026-adding">
<titleInfo>
<title>Adding ciofs and ciüfs to BOUQuET: Benchmark Extension to Ladin</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Frontull</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lara</namePart>
<namePart type="family">Castlunger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Oberhollenzer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Comploj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruth</namePart>
<namePart type="family">Videsott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Sama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Perathoner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlo</namePart>
<namePart type="family">Zoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Videsott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh Conference on Machine Translation</title>
</titleInfo>
<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">Philipp</namePart>
<namePart type="family">Koehn</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">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-474-3</identifier>
</relatedItem>
<abstract>Benchmarks do more than report scores: they provide a shared basis for evaluating methods, comparing systems, and measuring progress. As language technologies are now widely integrated into everyday life, efforts should also be made to include minority languages in the resources that underpin language-technology development. If languages are absent from relevant benchmarks, they remain harder to evaluate, compare, and incorporate into future language technologies. Expanding benchmark coverage is therefore essential for ensuring fair evaluation, increasing visibility, and enabling continued development of language technologies for these communities. To support MT development for Ladin, we contribute a Ladin extension of BOUQuET to the WMT 2026 OLDI shared task, covering the Val Badia and Gherdëina varieties. We present a systematic reference-creation workflow combining human translation, expert revision, cross-variant alignment, and blind ranking to produce high-quality references. The dataset is released under the CC BY-SA 4.0 license.</abstract>
<identifier type="citekey">frontull-etal-2026-adding</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.194/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2493</start>
<end>2504</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adding ciofs and ciüfs to BOUQuET: Benchmark Extension to Ladin
%A Frontull, Samuel
%A Castlunger, Lara
%A Oberhollenzer, Maximilian
%A Comploj, Karin
%A Videsott, Ruth
%A Sama, Robert
%A Perathoner, Gabriel
%A Zoli, Carlo
%A Videsott, Paul
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Eleventh Conference on Machine Translation
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-474-3
%F frontull-etal-2026-adding
%X Benchmarks do more than report scores: they provide a shared basis for evaluating methods, comparing systems, and measuring progress. As language technologies are now widely integrated into everyday life, efforts should also be made to include minority languages in the resources that underpin language-technology development. If languages are absent from relevant benchmarks, they remain harder to evaluate, compare, and incorporate into future language technologies. Expanding benchmark coverage is therefore essential for ensuring fair evaluation, increasing visibility, and enabling continued development of language technologies for these communities. To support MT development for Ladin, we contribute a Ladin extension of BOUQuET to the WMT 2026 OLDI shared task, covering the Val Badia and Gherdëina varieties. We present a systematic reference-creation workflow combining human translation, expert revision, cross-variant alignment, and blind ranking to produce high-quality references. The dataset is released under the CC BY-SA 4.0 license.
%U https://aclanthology.org/2026.wmt-main.194/
%P 2493-2504
Markdown (Informal)
[Adding ciofs and ciüfs to BOUQuET: Benchmark Extension to Ladin](https://aclanthology.org/2026.wmt-main.194/) (Frontull et al., WMT 2026)
ACL
- Samuel Frontull, Lara Castlunger, Maximilian Oberhollenzer, Karin Comploj, Ruth Videsott, Robert Sama, Gabriel Perathoner, Carlo Zoli, and Paul Videsott. 2026. Adding ciofs and ciüfs to BOUQuET: Benchmark Extension to Ladin. In Proceedings of the Eleventh Conference on Machine Translation, pages 2493–2504, Budapest, Hungary. Association for Computational Linguistics.