@inproceedings{zhang-2026-pages,
title = "Same Pages, Cleaner Labels: Language Identification for Eight Low-Resource Languages in m{C}4 and {F}ine{W}eb-2",
author = "Zhang, Gary",
editor = "Ortiz Suarez, Pedro and
Burchell, Laurie and
Ljube{\v{s}}i{\'c}, Nikola and
Scherrer, Yves and
Laippala, Veronika and
Dini{\'c}, Vuk and
Vaughan, Thom",
booktitle = "Proceedings of the 13th Web-as-Corpus Workshop",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wac-1.15/",
pages = "161--169",
ISBN = "979-8-89176-481-1",
abstract = "Low-resource subsets of multilingual web corpora often carry large amounts of text in the wrong language, and audits keep rediscovering the problem in each new corpus release. Scoring one corpus at a time cannot say whether a later corpus repeats an earlier one{'}s errors on the same documents. We join mC4 and FineWeb-2, built independently from overlapping Common Crawl snapshots, at the document level for eight low-resource languages. A URL join and a shift-invariant fingerprint sort the first 250k FineWeb-2 documents per language into three overlap classes: co-selected (same page, near-identical text), page-shared (same page, divergent text), and unmatched. Overlap covers 11{\%} to 74{\%} of a FineWeb-2 subset, so both corpora draw heavily on the same pages, and the shared documents are clean anyway. Under a criterion that flags a document only when two classifiers reject its label, 76.5{\%} of sampled mC4 Sundanese and 58.9{\%} of mC4 Kyrgyz are flagged, against at most 2.7{\%} of co-selected FineWeb-2 documents. We attribute the difference to selection at ingestion. Refiltering mC4 through GlotLID still leaves 0.7-17{\%} of survivors disagreeing with fastText for six languages, and barely moves Sundanese or Yoruba. We release the fingerprints, the flags, and the code: https://github.com/garyzhang1006/wac13-lid-overlap"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-2026-pages">
<titleInfo>
<title>Same Pages, Cleaner Labels: Language Identification for Eight Low-Resource Languages in mC4 and FineWeb-2</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gary</namePart>
<namePart type="family">Zhang</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 13th Web-as-Corpus Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Ortiz Suarez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurie</namePart>
<namePart type="family">Burchell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Laippala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vuk</namePart>
<namePart type="family">Dinić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thom</namePart>
<namePart type="family">Vaughan</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">979-8-89176-481-1</identifier>
</relatedItem>
<abstract>Low-resource subsets of multilingual web corpora often carry large amounts of text in the wrong language, and audits keep rediscovering the problem in each new corpus release. Scoring one corpus at a time cannot say whether a later corpus repeats an earlier one’s errors on the same documents. We join mC4 and FineWeb-2, built independently from overlapping Common Crawl snapshots, at the document level for eight low-resource languages. A URL join and a shift-invariant fingerprint sort the first 250k FineWeb-2 documents per language into three overlap classes: co-selected (same page, near-identical text), page-shared (same page, divergent text), and unmatched. Overlap covers 11% to 74% of a FineWeb-2 subset, so both corpora draw heavily on the same pages, and the shared documents are clean anyway. Under a criterion that flags a document only when two classifiers reject its label, 76.5% of sampled mC4 Sundanese and 58.9% of mC4 Kyrgyz are flagged, against at most 2.7% of co-selected FineWeb-2 documents. We attribute the difference to selection at ingestion. Refiltering mC4 through GlotLID still leaves 0.7-17% of survivors disagreeing with fastText for six languages, and barely moves Sundanese or Yoruba. We release the fingerprints, the flags, and the code: https://github.com/garyzhang1006/wac13-lid-overlap</abstract>
<identifier type="citekey">zhang-2026-pages</identifier>
<location>
<url>https://aclanthology.org/2026.wac-1.15/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>161</start>
<end>169</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Same Pages, Cleaner Labels: Language Identification for Eight Low-Resource Languages in mC4 and FineWeb-2
%A Zhang, Gary
%Y Ortiz Suarez, Pedro
%Y Burchell, Laurie
%Y Ljubešić, Nikola
%Y Scherrer, Yves
%Y Laippala, Veronika
%Y Dinić, Vuk
%Y Vaughan, Thom
%S Proceedings of the 13th Web-as-Corpus Workshop
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-481-1
%F zhang-2026-pages
%X Low-resource subsets of multilingual web corpora often carry large amounts of text in the wrong language, and audits keep rediscovering the problem in each new corpus release. Scoring one corpus at a time cannot say whether a later corpus repeats an earlier one’s errors on the same documents. We join mC4 and FineWeb-2, built independently from overlapping Common Crawl snapshots, at the document level for eight low-resource languages. A URL join and a shift-invariant fingerprint sort the first 250k FineWeb-2 documents per language into three overlap classes: co-selected (same page, near-identical text), page-shared (same page, divergent text), and unmatched. Overlap covers 11% to 74% of a FineWeb-2 subset, so both corpora draw heavily on the same pages, and the shared documents are clean anyway. Under a criterion that flags a document only when two classifiers reject its label, 76.5% of sampled mC4 Sundanese and 58.9% of mC4 Kyrgyz are flagged, against at most 2.7% of co-selected FineWeb-2 documents. We attribute the difference to selection at ingestion. Refiltering mC4 through GlotLID still leaves 0.7-17% of survivors disagreeing with fastText for six languages, and barely moves Sundanese or Yoruba. We release the fingerprints, the flags, and the code: https://github.com/garyzhang1006/wac13-lid-overlap
%U https://aclanthology.org/2026.wac-1.15/
%P 161-169
Markdown (Informal)
[Same Pages, Cleaner Labels: Language Identification for Eight Low-Resource Languages in mC4 and FineWeb-2](https://aclanthology.org/2026.wac-1.15/) (Zhang, WAC 2026)
ACL