@inproceedings{karaosmanoglu-2026-extraction,
title = "Extraction Changes the Route: Main-Content Extraction and Language Identification in Web Corpora",
author = "Karaosmano{\u{g}}lu, Toprak Seda",
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-1.26/",
pages = "297--307",
ISBN = "979-8-89176-481-1",
abstract = "Main-content extraction commonly precedes language identification (LID) and determines its input in web-corpus pipelines. We measure this dependency on 7,808 WebMainBench pages using three extractors and three LID systems. We compare human-selected main text with annotated-region and full-page extractor outputs. A context flip occurs when annotated-region extraction preserves the route on human-selected text but full-page extraction changes it. For pages with nonempty text and matching human-selected and annotated-region routes, context-flip rates are 1.10{--}3.20{\%}. On the common eligible set, Magic-HTML has lower paired rates than Trafilatura for all three LID systems, with each corresponding 95{\%} interval excluding zero. All-page route loss counts empty outputs or routes that differ from the route on human-selected text. Magic-HTML{'}s empty full-page outputs add 5.84 percentage points. The fixed snapshot{'}s coarse non{\_}en{--}en difference is positive in all nine configurations and remains positive after standardization to the page-complexity field (meta.level). A 100-page audit finds 35 unsupported, 29 supported, and 36 indeterminate routes. Of 35 unsupported flips, 26 move from predicted English to another route, and 17 involve changed content selection alone or in mixed cases. Among supported flips, 21 move to English. Extraction context can change text availability and downstream routing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karaosmanoglu-2026-extraction">
<titleInfo>
<title>Extraction Changes the Route: Main-Content Extraction and Language Identification in Web Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toprak</namePart>
<namePart type="given">Seda</namePart>
<namePart type="family">Karaosmanoğlu</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>Main-content extraction commonly precedes language identification (LID) and determines its input in web-corpus pipelines. We measure this dependency on 7,808 WebMainBench pages using three extractors and three LID systems. We compare human-selected main text with annotated-region and full-page extractor outputs. A context flip occurs when annotated-region extraction preserves the route on human-selected text but full-page extraction changes it. For pages with nonempty text and matching human-selected and annotated-region routes, context-flip rates are 1.10–3.20%. On the common eligible set, Magic-HTML has lower paired rates than Trafilatura for all three LID systems, with each corresponding 95% interval excluding zero. All-page route loss counts empty outputs or routes that differ from the route on human-selected text. Magic-HTML’s empty full-page outputs add 5.84 percentage points. The fixed snapshot’s coarse non_en–en difference is positive in all nine configurations and remains positive after standardization to the page-complexity field (meta.level). A 100-page audit finds 35 unsupported, 29 supported, and 36 indeterminate routes. Of 35 unsupported flips, 26 move from predicted English to another route, and 17 involve changed content selection alone or in mixed cases. Among supported flips, 21 move to English. Extraction context can change text availability and downstream routing.</abstract>
<identifier type="citekey">karaosmanoglu-2026-extraction</identifier>
<location>
<url>https://aclanthology.org/2026.wac-1.26/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>297</start>
<end>307</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extraction Changes the Route: Main-Content Extraction and Language Identification in Web Corpora
%A Karaosmanoğlu, Toprak Seda
%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 karaosmanoglu-2026-extraction
%X Main-content extraction commonly precedes language identification (LID) and determines its input in web-corpus pipelines. We measure this dependency on 7,808 WebMainBench pages using three extractors and three LID systems. We compare human-selected main text with annotated-region and full-page extractor outputs. A context flip occurs when annotated-region extraction preserves the route on human-selected text but full-page extraction changes it. For pages with nonempty text and matching human-selected and annotated-region routes, context-flip rates are 1.10–3.20%. On the common eligible set, Magic-HTML has lower paired rates than Trafilatura for all three LID systems, with each corresponding 95% interval excluding zero. All-page route loss counts empty outputs or routes that differ from the route on human-selected text. Magic-HTML’s empty full-page outputs add 5.84 percentage points. The fixed snapshot’s coarse non_en–en difference is positive in all nine configurations and remains positive after standardization to the page-complexity field (meta.level). A 100-page audit finds 35 unsupported, 29 supported, and 36 indeterminate routes. Of 35 unsupported flips, 26 move from predicted English to another route, and 17 involve changed content selection alone or in mixed cases. Among supported flips, 21 move to English. Extraction context can change text availability and downstream routing.
%U https://aclanthology.org/2026.wac-1.26/
%P 297-307
Markdown (Informal)
[Extraction Changes the Route: Main-Content Extraction and Language Identification in Web Corpora](https://aclanthology.org/2026.wac-1.26/) (Karaosmanoğlu, WAC 2026)
ACL