@proceedings{cmlc-2026-1,
    title = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.0/"
}
@inproceedings{rinaldi-etal-2026-testimole,
    title = "{T}esti{M}ole-Conversational: A 30-Billion-Word {I}talian Discussion Board Corpus (1996{--}2024) for Language Modeling and Sociolinguistic Research",
    author = "Rinaldi, Matteo  and
      Varvara, Rossella  and
      Patti, Viviana",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.1/",
    doi = "10.63317/5643evropidu",
    pages = "1--11"
}
@inproceedings{koeva-stoyanova-2026-large,
    title = "A Large Dataset Representing {B}ulgarian, with the {B}ulgarian National Corpus as Its Core",
    author = "Koeva, Svetla Peneva  and
      Stoyanova, Ivelina",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.2/",
    doi = "10.63317/4gxqpsnk5jz5",
    pages = "12--24"
}
@inproceedings{kabashi-ruppert-2026-merimenga,
    title = {Merim{\"e}nga: A Manifest-First Pipeline for Reproducible {A}lbanian Web Corpus Construction},
    author = "Kabashi, Besim  and
      Ruppert, Michael",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.3/",
    doi = "10.63317/4aesmyqqveeo",
    pages = "25--31"
}
@inproceedings{schneider-2026-pop,
    title = "Pop Lyrics through Time: Challenges in Corpus-Based Modeling of Linguistic and Emotional Dynamics in {G}erman Pop Lyrics",
    author = "Schneider, Roman",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.4/",
    doi = "10.63317/4dh6sfnuqcnr",
    pages = "32--43"
}
@inproceedings{dargis-valkovska-2026-infrastructure,
    title = "The Infrastructure behind {L}atvian National Corpora Collection",
    author = "Dargis, Roberts  and
      Valkovska, Baiba",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.5/",
    doi = "10.63317/4cz3r3aih2t9",
    pages = "44--48"
}
@inproceedings{dadason-steingrimsson-2026-optimized,
    title = "Optimized for {AI}: Curating the {I}celandic {G}igaword Corpus for Stable {LLM} Training",
    author = "Da{\dh}ason, J{\'o}n Fri{\dh}rik  and
      Steingr{\'i}msson, Stein{\th}{\'o}r",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.6/",
    doi = "10.63317/3uatbht8mdrf",
    pages = "49--56"
}
@inproceedings{gavriilidou-sidiropoulos-2026-hellenic,
    title = "{H}ellenic National Corpus: The Current State",
    author = "Gavriilidou, Maria  and
      Sidiropoulos, Nikolaos",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.7/",
    doi = "10.63317/492hm739pspc",
    pages = "57--62"
}
@inproceedings{o-meachair-etal-2026-corpas,
    title = "Corpas N{\'a}isi{\'u}nta {N}a Gaeilge 2022-2029: A Project Overview",
    author = "{\'O} Meachair, M{\'i}che{\'a}l J.  and
      Bhreathnach, {\'U}na  and
      Scannell, Kevin  and
      Mechura, Michal  and
      {\'O} Raghallaigh, Brian  and
      {\'O} Cleirc{\'i}n, Gear{\'o}id",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.8/",
    doi = "10.63317/4ybzkgmrs3hd",
    pages = "63--65"
}
@inproceedings{shvedova-2026-general,
    title = "General Regionally Annotated Corpus of {U}krainian: Recent Developments and Future Plans",
    author = "Shvedova, Maria",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.9/",
    doi = "10.63317/2qtbabb3qtjw",
    pages = "66--70"
}
@inproceedings{koeva-stoyanova-2026-recent,
    title = "Recent Developments of the {B}ulgarian National Corpus",
    author = "Koeva, Svetla Peneva  and
      Stoyanova, Ivelina",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.10/",
    doi = "10.63317/3m95ohtw7mjs",
    pages = "71--75"
}
@inproceedings{wynne-bushnell-2026-british,
    title = "The {B}ritish {N}ational {C}orpus 1994 to 2026",
    author = "Wynne, Martin  and
      Bushnell, Megan",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.11/",
    doi = "10.63317/4yzqikwnh4b8",
    pages = "76--77"
}
@inproceedings{kieras-etal-2026-corpus-contemporary,
    title = "The Corpus of Contemporary {P}olish: 2011-2020 Decade and Beyond",
    author = "Kiera{\'s}, Witold  and
      Marciniak, Ma{\l}gorzata  and
      Krasnowska-Kiera{\'s}, Katarzyna  and
      Woli{\'n}ski, Marcin",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.12/",
    doi = "10.63317/35cjnfgvskp4",
    pages = "78--79"
}
@inproceedings{tadic-etal-2026-building,
    title = "Building the v4 of the {C}roatian National Corpus",
    author = "Tadi{\'c}, Marko  and
      {\v{S}}tefanec, Vanja  and
      Farka{\v{s}}, Da{\v{s}}a",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.13/",
    doi = "10.63317/48si6yrozisf",
    pages = "80--83"
}
@inproceedings{ligeti-nagy-etal-2026-managing,
    title = "Managing Growth in a National Corpus: The {H}ungarian National Corpus 3.0 ({MNSZ}3)",
    author = {Ligeti-Nagy, No{\'e}mi  and
      H{\'e}ja, Enik{\H{o}}  and
      B{\'a}nfi, {\'A}gnes  and
      F{\"o}ldesi, Fl{\'o}ra  and
      S{\'a}rossy, Bence  and
      Skrab{\'a}k, Bogl{\'a}rka  and
      V{\'a}radi, Tam{\'a}s  and
      Pr{\'o}sz{\'e}ky, G{\'a}bor},
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.14/",
    doi = "10.63317/46aafswuwv4m",
    pages = "84--90"
}
@inproceedings{irimia-etal-2026-corola,
    title = "{C}o{R}o{L}a Version 2.0: Corpus Enrichment and a New Annotation Level",
    author = "Irimia, Elena  and
      Barbu Mititelu, Verginica  and
      Ion, Radu  and
      Pais, Vasile  and
      Mitrofan, Maria  and
      Tufis, Dan Ioan",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.15/",
    doi = "10.63317/44pgxmuvou8v",
    pages = "91--97"
}
@inproceedings{hofenbitzer-etal-2026-german,
    title = "The {G}erman Medical Text Corpus: Early 2026 Update",
    author = {Hofenbitzer, Justin  and
      Lohr, Christina  and
      Meineke, Frank  and
      L{\"o}ffler, Markus  and
      Boeker, Martin},
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.16/",
    doi = "10.63317/3xopdv4wdd93",
    pages = "98--100"
}
@inproceedings{knight-alva-manchego-2026-corpus,
    title = "From Corpus to Community: New {NLP} Tools for {W}elsh Language Research and Learning",
    author = "Knight, Dawn  and
      Alva-Manchego, Fernando",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.17/",
    doi = "10.63317/56urzbii2rvy",
    pages = "101--103"
}
@inproceedings{krasselt-etal-2026-swiss,
    title = "{S}wiss-{AL}: Language Data Platform for Applied Sciences",
    author = {Krasselt, Julia  and
      Dreesen, Philipp  and
      Lemmenmeier-Batini{\'c}, Dolores  and
      Geckeler, Sooyeon  and
      Rothenh{\"a}usler, Klaus  and
      Fluor, Matthias},
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.18/",
    doi = "10.63317/5omeepsboek4",
    pages = "104--105"
}
@inproceedings{kupietz-etal-2026-eureco,
    title = "{E}u{R}e{C}o, {K}or{AP} and {D}e{R}e{K}o: Updates on Ingestion and Annotation Pipelines, Backend, Interfaces, Operation, and Corpora",
    author = {Kupietz, Marc  and
      Diewald, Nils  and
      L{\"u}ngen, Harald  and
      Margaretha Illig, Eliza  and
      Stallkamp, Helge  and
      Tran, Uyen-Nhu  and
      Yaddehige, Rameela},
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://aclanthology.org/2026.cmlc-1.19/",
    doi = "10.63317/2xcbb5knp2mi",
    pages = "106--112"
}