@inproceedings{marmonier-etal-2026-french,
title = "A {F}rench Version of the {S}mol{S}ent Corpus",
author = "Marmonier, Malik and
Bawden, Rachel and
Sagot, Beno{\^i}t",
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.197/",
pages = "2517--2526",
ISBN = "979-8-89176-474-3",
abstract = "We present a French version of the SmolSent corpus, a contribution to the WMT 2026 Open Language Data Initiative (OLDI) shared task. Originally curated to maximize unique-word coverage across 863 English sentences, SmolSent constitutes a valuable, token-efficient training set for the machine translation of low-resource languages. We describe our translation workflow, which relied on a custom-built interface to select and refine translation hypotheses generated by a traditional encoder-decoder model, alongside two state-of-the-art reasoning-enabled large language models (LLMs). Experimental validation based on the MetricX-24-XXL model for quality estimation, supported by bootstrap resampling significance tests, indicates that human post-editing results in significant quality improvements over all raw model outputs, even as reasoning models like Gemma-4-31B-it achieve a competitive 39.51{\%} zero-edit rate. This French partition is not an end in itself, but a pivot resource meant to facilitate ongoing data collection efforts for under-resourced regional languages of France, such as Savoyard and Gallo."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marmonier-etal-2026-french">
<titleInfo>
<title>A French Version of the SmolSent Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Malik</namePart>
<namePart type="family">Marmonier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoît</namePart>
<namePart type="family">Sagot</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>We present a French version of the SmolSent corpus, a contribution to the WMT 2026 Open Language Data Initiative (OLDI) shared task. Originally curated to maximize unique-word coverage across 863 English sentences, SmolSent constitutes a valuable, token-efficient training set for the machine translation of low-resource languages. We describe our translation workflow, which relied on a custom-built interface to select and refine translation hypotheses generated by a traditional encoder-decoder model, alongside two state-of-the-art reasoning-enabled large language models (LLMs). Experimental validation based on the MetricX-24-XXL model for quality estimation, supported by bootstrap resampling significance tests, indicates that human post-editing results in significant quality improvements over all raw model outputs, even as reasoning models like Gemma-4-31B-it achieve a competitive 39.51% zero-edit rate. This French partition is not an end in itself, but a pivot resource meant to facilitate ongoing data collection efforts for under-resourced regional languages of France, such as Savoyard and Gallo.</abstract>
<identifier type="citekey">marmonier-etal-2026-french</identifier>
<location>
<url>https://aclanthology.org/2026.wmt-main.197/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2517</start>
<end>2526</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A French Version of the SmolSent Corpus
%A Marmonier, Malik
%A Bawden, Rachel
%A Sagot, Benoît
%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 marmonier-etal-2026-french
%X We present a French version of the SmolSent corpus, a contribution to the WMT 2026 Open Language Data Initiative (OLDI) shared task. Originally curated to maximize unique-word coverage across 863 English sentences, SmolSent constitutes a valuable, token-efficient training set for the machine translation of low-resource languages. We describe our translation workflow, which relied on a custom-built interface to select and refine translation hypotheses generated by a traditional encoder-decoder model, alongside two state-of-the-art reasoning-enabled large language models (LLMs). Experimental validation based on the MetricX-24-XXL model for quality estimation, supported by bootstrap resampling significance tests, indicates that human post-editing results in significant quality improvements over all raw model outputs, even as reasoning models like Gemma-4-31B-it achieve a competitive 39.51% zero-edit rate. This French partition is not an end in itself, but a pivot resource meant to facilitate ongoing data collection efforts for under-resourced regional languages of France, such as Savoyard and Gallo.
%U https://aclanthology.org/2026.wmt-main.197/
%P 2517-2526
Markdown (Informal)
[A French Version of the SmolSent Corpus](https://aclanthology.org/2026.wmt-main.197/) (Marmonier et al., WMT 2026)
ACL
- Malik Marmonier, Rachel Bawden, and Benoît Sagot. 2026. A French Version of the SmolSent Corpus. In Proceedings of the Eleventh Conference on Machine Translation, pages 2517–2526, Budapest, Hungary. Association for Computational Linguistics.