@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",
abstract = {We present Merim{\"e}nga, a pipeline for reproducible Albanian web-corpus construction from Common Crawl. Rather than distributing a static text dump, we publish versioned manifests and append-only JSONL ledgers that make every retrieval and filtering decision replayable at record level. Records are addressed by (WARC filename, byte offset, byte length) and retrieved via HTTP range requests with checksum validation, enabling selective download, resumability, and exact re-materialization. On top of deterministic cleaning and deduplication, Merim{\"e}nga supports teacher{--}student filtering: a large LLM labels a stratified sample; the resulting policy is distilled into a faster student model applied at corpus scale. The paper contributes (i) a reproducibility specification for web-corpus construction based on coordinate-addressed retrieval and decision ledgers, (ii) a concrete instantiation for Albanian with language-specific filtering, and (iii) an evaluation protocol for rerun equivalence and filter-stack ablation. Large-scale download and full-corpus filtering are ongoing; this submission focuses on methodology and auditable artifacts rather than final corpus statistics.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kabashi-ruppert-2026-merimenga">
<titleInfo>
<title>Merimënga: A Manifest-First Pipeline for Reproducible Albanian Web Corpus Construction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Besim</namePart>
<namePart type="family">Kabashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Ruppert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Bański</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawn</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Kupietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Witt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Wróblewska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present Merimënga, a pipeline for reproducible Albanian web-corpus construction from Common Crawl. Rather than distributing a static text dump, we publish versioned manifests and append-only JSONL ledgers that make every retrieval and filtering decision replayable at record level. Records are addressed by (WARC filename, byte offset, byte length) and retrieved via HTTP range requests with checksum validation, enabling selective download, resumability, and exact re-materialization. On top of deterministic cleaning and deduplication, Merimënga supports teacher–student filtering: a large LLM labels a stratified sample; the resulting policy is distilled into a faster student model applied at corpus scale. The paper contributes (i) a reproducibility specification for web-corpus construction based on coordinate-addressed retrieval and decision ledgers, (ii) a concrete instantiation for Albanian with language-specific filtering, and (iii) an evaluation protocol for rerun equivalence and filter-stack ablation. Large-scale download and full-corpus filtering are ongoing; this submission focuses on methodology and auditable artifacts rather than final corpus statistics.</abstract>
<identifier type="citekey">kabashi-ruppert-2026-merimenga</identifier>
<identifier type="doi">10.63317/4aesmyqqveeo</identifier>
<location>
<url>https://aclanthology.org/2026.cmlc-1.3/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>25</start>
<end>31</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Merimënga: A Manifest-First Pipeline for Reproducible Albanian Web Corpus Construction
%A Kabashi, Besim
%A Ruppert, Michael
%Y Bański, Piotr
%Y Knight, Dawn
%Y Kupietz, Marc
%Y Witt, Andreas
%Y Wróblewska, Alina
%S Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F kabashi-ruppert-2026-merimenga
%X We present Merimënga, a pipeline for reproducible Albanian web-corpus construction from Common Crawl. Rather than distributing a static text dump, we publish versioned manifests and append-only JSONL ledgers that make every retrieval and filtering decision replayable at record level. Records are addressed by (WARC filename, byte offset, byte length) and retrieved via HTTP range requests with checksum validation, enabling selective download, resumability, and exact re-materialization. On top of deterministic cleaning and deduplication, Merimënga supports teacher–student filtering: a large LLM labels a stratified sample; the resulting policy is distilled into a faster student model applied at corpus scale. The paper contributes (i) a reproducibility specification for web-corpus construction based on coordinate-addressed retrieval and decision ledgers, (ii) a concrete instantiation for Albanian with language-specific filtering, and (iii) an evaluation protocol for rerun equivalence and filter-stack ablation. Large-scale download and full-corpus filtering are ongoing; this submission focuses on methodology and auditable artifacts rather than final corpus statistics.
%R 10.63317/4aesmyqqveeo
%U https://aclanthology.org/2026.cmlc-1.3/
%U https://doi.org/10.63317/4aesmyqqveeo
%P 25-31
Markdown (Informal)
[Merimënga: A Manifest-First Pipeline for Reproducible Albanian Web Corpus Construction](https://aclanthology.org/2026.cmlc-1.3/) (Kabashi & Ruppert, CMLC 2026)
ACL