@inproceedings{sobhy-2026-frenchnews,
title = "{F}rench{N}ews-7: Benchmarking Cross-Publisher {F}rench News Editorial Desk Classification",
author = "Sobhy, Amr",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.91/",
pages = "1982--1997",
ISBN = "979-8-89176-439-2",
abstract = "We present FrenchNews-7, a cross-publisher France-based French-language news editorial desk classification benchmark combining a large multi-outlet corpus, a URL-derived seven-class taxonomy, and a fine-tuned CamemBERT classifier. Labels are assigned via a hybrid pipeline combining publisher URL slugs with LLM annotation for structurally ambiguous cases, audited through an inter-rater study (2 humans + 2 LLMs; pairwise {\ensuremath{\kappa}} {\ensuremath{\geq}} 0.766, human{--}human {\ensuremath{\kappa}} = 0.806). We evaluate lexical, multilingual, and French-specific trained classifiers under both in-distribution and held-out-publisher settings, with additional comparison against zero-shot LLM baselines (GPT-OSS-120B, Mistral Small 3.2, Llama-3.3-70B) on the held-out pool. The strongest model, CamemBERT-base on full article text, outperforms headline-only input, generalizes to unseen outlets, and exceeds all three zero-shot LLM baselines on overall recall (0.799), with the gap concentrated in the ambiguous editorial-boundary categories {\'E}conomie and Soci{\'e}t{\'e}. Cross-publisher evaluation reveals uneven boundary stability: Sport, Culture Loisirs, and International transfer cleanly, while {\'E}conomie (recall = 0.517) is statistically indistinguishable from blinded human agreement on the same articles (0.55, n = 40), and Soci{\'e}t{\'e} (precision = 0.577) absorbs boundary ambiguity, both suggesting editorial conventions rather than recoverable classifier headroom. The fine-tuned CamemBERT-base model is released on Hugging Face (https://huggingface.co/LeFrenchNewsLab/camembert-base-frenchnews7) and the labeled manifest on (https://huggingface.co/datasets/LeFrenchNewsLab/frenchnews-7), alongside reference collection scripts to assist re-fetching and a reliability-tier guidance table."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sobhy-2026-frenchnews">
<titleInfo>
<title>FrenchNews-7: Benchmarking Cross-Publisher French News Editorial Desk Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Sobhy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>We present FrenchNews-7, a cross-publisher France-based French-language news editorial desk classification benchmark combining a large multi-outlet corpus, a URL-derived seven-class taxonomy, and a fine-tuned CamemBERT classifier. Labels are assigned via a hybrid pipeline combining publisher URL slugs with LLM annotation for structurally ambiguous cases, audited through an inter-rater study (2 humans + 2 LLMs; pairwise \ensuremathąppa \ensuremath\geq 0.766, human–human \ensuremathąppa = 0.806). We evaluate lexical, multilingual, and French-specific trained classifiers under both in-distribution and held-out-publisher settings, with additional comparison against zero-shot LLM baselines (GPT-OSS-120B, Mistral Small 3.2, Llama-3.3-70B) on the held-out pool. The strongest model, CamemBERT-base on full article text, outperforms headline-only input, generalizes to unseen outlets, and exceeds all three zero-shot LLM baselines on overall recall (0.799), with the gap concentrated in the ambiguous editorial-boundary categories Économie and Société. Cross-publisher evaluation reveals uneven boundary stability: Sport, Culture Loisirs, and International transfer cleanly, while Économie (recall = 0.517) is statistically indistinguishable from blinded human agreement on the same articles (0.55, n = 40), and Société (precision = 0.577) absorbs boundary ambiguity, both suggesting editorial conventions rather than recoverable classifier headroom. The fine-tuned CamemBERT-base model is released on Hugging Face (https://huggingface.co/LeFrenchNewsLab/camembert-base-frenchnews7) and the labeled manifest on (https://huggingface.co/datasets/LeFrenchNewsLab/frenchnews-7), alongside reference collection scripts to assist re-fetching and a reliability-tier guidance table.</abstract>
<identifier type="citekey">sobhy-2026-frenchnews</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.91/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1982</start>
<end>1997</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FrenchNews-7: Benchmarking Cross-Publisher French News Editorial Desk Classification
%A Sobhy, Amr
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F sobhy-2026-frenchnews
%X We present FrenchNews-7, a cross-publisher France-based French-language news editorial desk classification benchmark combining a large multi-outlet corpus, a URL-derived seven-class taxonomy, and a fine-tuned CamemBERT classifier. Labels are assigned via a hybrid pipeline combining publisher URL slugs with LLM annotation for structurally ambiguous cases, audited through an inter-rater study (2 humans + 2 LLMs; pairwise \ensuremathąppa \ensuremath\geq 0.766, human–human \ensuremathąppa = 0.806). We evaluate lexical, multilingual, and French-specific trained classifiers under both in-distribution and held-out-publisher settings, with additional comparison against zero-shot LLM baselines (GPT-OSS-120B, Mistral Small 3.2, Llama-3.3-70B) on the held-out pool. The strongest model, CamemBERT-base on full article text, outperforms headline-only input, generalizes to unseen outlets, and exceeds all three zero-shot LLM baselines on overall recall (0.799), with the gap concentrated in the ambiguous editorial-boundary categories Économie and Société. Cross-publisher evaluation reveals uneven boundary stability: Sport, Culture Loisirs, and International transfer cleanly, while Économie (recall = 0.517) is statistically indistinguishable from blinded human agreement on the same articles (0.55, n = 40), and Société (precision = 0.577) absorbs boundary ambiguity, both suggesting editorial conventions rather than recoverable classifier headroom. The fine-tuned CamemBERT-base model is released on Hugging Face (https://huggingface.co/LeFrenchNewsLab/camembert-base-frenchnews7) and the labeled manifest on (https://huggingface.co/datasets/LeFrenchNewsLab/frenchnews-7), alongside reference collection scripts to assist re-fetching and a reliability-tier guidance table.
%U https://aclanthology.org/2026.aacl-long.91/
%P 1982-1997
Markdown (Informal)
[FrenchNews-7: Benchmarking Cross-Publisher French News Editorial Desk Classification](https://aclanthology.org/2026.aacl-long.91/) (Sobhy, AACL-IJCNLP 2026)
ACL