@proceedings{wac-2026-1,
    title = "Proceedings of the 13th Web-as-Corpus Workshop",
    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",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.wac-1.0/",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{tichy-libovicky-2026-chalis,
    title = "{CHALIS}: A Challenge Dataset for Language Identification in Difficult Scenarios",
    author = "Tich{\'y}, Michal  and
      Libovick{\'y}, Jind{\v{r}}ich",
    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-1.1/",
    pages = "1--7",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{charalampous-djouvas-2026-createdebate,
    title = "The {C}reate{D}ebate Arguments Dataset: A Large-Scale Naturalistic Corpus for Computational Argumentation",
    author = "Charalampous, Antonis  and
      Djouvas, Constantinos",
    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-1.2/",
    pages = "8--21",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{sobhy-2026-published,
    title = "Who Published This Headline? Editorial Fingerprinting in {F}rench News Under Topic Control",
    author = "Sobhy, Amr",
    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-1.3/",
    pages = "22--36",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{raihan-etal-2026-taxonomy,
    title = "A Taxonomy of Programming Languages for Code Generation",
    author = "Raihan, Nishat  and
      Newman, Christian  and
      Zampieri, Marcos",
    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-1.4/",
    pages = "37--52",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{ljubesic-etal-2026-persists,
    title = "What Persists across Web Crawls? Genre and News Topic Variation in {S}outh {S}lavic Web Corpora",
    author = "Ljube{\v{s}}i{\'c}, Nikola  and
      Dini{\'c}, Vuk  and
      Rupnik, Peter",
    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-1.5/",
    pages = "53--59",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{razzaghi-etal-2026-hplt3,
    title = "{HPLT}3-{P}er{R}ef: A Refined Large-Scale {P}ersian Web Corpus via Supervised Document Quality Filtering",
    author = "Razzaghi, Alireza  and
      Galica, Tomasz  and
      Henriksson, Erik  and
      Laippala, Veronika",
    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-1.6/",
    pages = "60--69",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{ostendorff-2026-host,
    title = "Host-Aware Web Crawling for {LLM} Pretraining Data",
    author = "Ostendorff, Malte",
    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-1.7/",
    pages = "70--87",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{li-etal-2026-auditing,
    title = "Auditing Source Exposure in {B}aidu and {G}oogle {AI} Search",
    author = "Li, Yibo  and
      Guan, Enci  and
      Cai, Yuedan  and
      Liu, Geng  and
      Pierri, Francesco",
    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-1.8/",
    pages = "88--99",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{zhang-2026-lost,
    title = "Lost in Translation: Structured-Span Corruption in Machine-Translated Multilingual Web Corpora",
    author = "Zhang, Ruiyang",
    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-1.9/",
    pages = "100--106",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{foppiano-2026-counting,
    title = "Counting Documents Is Not Counting Text: Unit Bias in Web-{PDF} Corpus Statistics",
    author = "Foppiano, Luca",
    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-1.10/",
    pages = "107--114",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{kunnas-etal-2026-educational,
    title = "Is Educational Content Enough? The Linguistic and Thematic Effects of Educational Filtering",
    author = "Kunnas, Urho  and
      Laippala, Veronika  and
      Pyysalo, Sampo  and
      Galica, Tomasz",
    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-1.11/",
    pages = "115--130",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{dahal-etal-2026-wincc,
    title = "{W}i{NCC}: A Reproducible Pipeline for Constructing a {W}ikipedia-enriched {N}epali Cross-lingual Corpus",
    author = "Dahal, Ahrnish P  and
      Baranwal, Pushkar  and
      Pundir, Amit  and
      Jain Saxena, Geetika  and
      Singh, Sanjeev",
    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-1.12/",
    pages = "131--138",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{birkenes-2026-mapping,
    title = "Mapping {S}{\'a}mi Languages in a {N}orwegian National Web Crawl: Results from a Representativeness Study",
    author = "Birkenes, Magnus Breder",
    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-1.13/",
    pages = "139--146",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{kanner-etal-2026-towards,
    title = "Towards More Reliable Web Metadata: Do Register Classifiers Learn Register or Genre Features?",
    author = "Kanner, Antti  and
      Lundberg, Tuomas  and
      Henriksson, Erik  and
      Laippala, Veronika",
    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-1.14/",
    pages = "147--160",
    ISBN = "979-8-89176-481-1"
}
@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"
}
@inproceedings{zhang-2026-many,
    title = "How Many Duplicates Are Left? Capture-Recapture and Sampling Inversion for Residual Duplication in {F}ine{W}eb",
    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-1.16/",
    pages = "170--181",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{flesch-2026-using,
    title = "Using Search Engines to Trace Metalinguistic Discussions of the Noun ``Female'' in Digital Discourse",
    author = "Flesch, Marie",
    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-1.17/",
    pages = "182--191",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{coats-2026-keeping,
    title = "Keeping the Ums: Conversation-Analysis-Informed Verbatim {ASR} for Web Speech",
    author = "Coats, Steven",
    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-1.18/",
    pages = "192--199",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{henriksson-etal-2026-segment,
    title = "Segment-Level Register Analysis of the Multilingual Web",
    author = "Henriksson, Erik  and
      Razzaghi, Alireza  and
      Galica, Tomasz  and
      Guo, Jiaqi Feng  and
      Dong, Anastasia Zhi-Ling  and
      Kunnas, Urho  and
      Psaltaki, Erofili  and
      Lundberg, Tuomas  and
      Kanner, Antti  and
      Laippala, Veronika",
    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-1.19/",
    pages = "200--213",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{goyal-2026-invisible,
    title = "Invisible on the Web: An Audit of Low-Resource Muskogean Languages in Web-Crawled Corpora",
    author = "Goyal, Sharvin",
    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-1.20/",
    pages = "214--219",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{goyal-2026-crawl,
    title = "The Crawl Gap: Where Endangered-Language Web Content Is Lost Before It Reaches a Corpus",
    author = "Goyal, Sharvin",
    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-1.21/",
    pages = "220--223",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{zhou-etal-2026-tell,
    title = "You Can Tell Who{'}s Asking: What the Web{'}s Questions Are Made Of, and Where They Come From",
    author = "Zhou, Calvin  and
      McCloskey, Vincent  and
      Srinivasan, Krishna",
    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-1.22/",
    pages = "224--237",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{wong-2026-wiktionary,
    title = "{W}iktionary as a Crowdsourced Lexicon for {E}nglish Dialects",
    author = "Wong, Sidney",
    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-1.23/",
    pages = "238--251",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{tarkka-etal-2026-task,
    title = "Task-Agnostic Web Document Annotation with {LLM}-Generated Descriptors",
    author = "Tarkka, Otto  and
      Henriksson, Erik  and
      Kanerva, Jenna  and
      Ginter, Filip",
    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-1.24/",
    pages = "252--281",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{chernikov-etal-2026-pawn,
    title = "{PAWN}++ in the Wild: Evaluating {AI}-Generated Text Detection on the Web",
    author = "Chernikov, Oleg  and
      Ptitsyn, Evgenii  and
      Burlova, Albina",
    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-1.25/",
    pages = "282--296",
    ISBN = "979-8-89176-481-1"
}
@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"
}
@inproceedings{sivakulasingam-etal-2026-ceynews,
    title = "{C}ey{N}ews: A {S}ri {L}ankan Trilingual News Corpus",
    author = "Sivakulasingam, Ajintha  and
      Sarveswaran, Kengatharaiyer  and
      Ranasinghe, Tharindu",
    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-1.27/",
    pages = "308--319",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{wang-2026-probing,
    title = "Probing Pretraining ``Quality'': Sociolinguistic Mobility as a Lens on Web Corpus Filters",
    author = "Wang, Jessica",
    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-1.28/",
    pages = "320--330",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{rigal-ginzburg-2026-web,
    title = "A Web-Derived Typology of Multimodal Infant Crying: Taxonomy, a Text-Only Web-Corpus Comparison, and Ethical Issues",
    author = "Rigal, Jacob  and
      Ginzburg, Jonathan",
    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-1.29/",
    pages = "331--346",
    ISBN = "979-8-89176-481-1"
}
@inproceedings{zhang-cheng-2026-whose,
    title = "Whose Robots.txt? Consent-Infrastructure Inequality Across the Languages of Web Corpora",
    author = "Zhang, Gary  and
      Cheng, Austin",
    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-1.30/",
    pages = "347--355",
    ISBN = "979-8-89176-481-1"
}