@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",
abstract = "WiNCC is a reproducible and automatic construction pipeline for building an English{--}Nepali cross-lingual retrieval corpus that is difficulty-aware, relying on public Wikipedia and Wikidata. Part 1 reproduces a CLIRMatrix-style baseline. Nepali Wikipedia was crawled, articles resolved to a Wikidata QID, then intersected with Wikidata sitelinks to obtain Nepali{--}English query pairs and the corresponding English document corpus. These were sampled into gold pairs and padded with random English distractors to form a document baseline corpus. Part 2 adds a data-enrichment stage to Part 1 with multi-query, class-matched hard negatives. We compare the produced corpus against existing cross-lingual retrieval resources, run cross-lingual retrieval baselines with three distinct multilingual embedding models (BGE-M3, multilingual-E5-large, and Qwen3-Embedding-4B), and analyze slice-wise quality metadata and query-type-wise field metrics supporting the corpus{'}s use as a difficulty-aware benchmark. Through our corpus, we also find (1) a 27.8{--}41.5-point NDCG@10 drop from English to Nepali, (2) descriptions are 5{--}6{\texttimes} harder than titles, and (3) hard negatives are 2{\texttimes} stickier than random distractors."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dahal-etal-2026-wincc">
<titleInfo>
<title>WiNCC: A Reproducible Pipeline for Constructing a Wikipedia-enriched Nepali Cross-lingual Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahrnish</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Dahal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushkar</namePart>
<namePart type="family">Baranwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Pundir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geetika</namePart>
<namePart type="family">Jain Saxena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeev</namePart>
<namePart type="family">Singh</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>WiNCC is a reproducible and automatic construction pipeline for building an English–Nepali cross-lingual retrieval corpus that is difficulty-aware, relying on public Wikipedia and Wikidata. Part 1 reproduces a CLIRMatrix-style baseline. Nepali Wikipedia was crawled, articles resolved to a Wikidata QID, then intersected with Wikidata sitelinks to obtain Nepali–English query pairs and the corresponding English document corpus. These were sampled into gold pairs and padded with random English distractors to form a document baseline corpus. Part 2 adds a data-enrichment stage to Part 1 with multi-query, class-matched hard negatives. We compare the produced corpus against existing cross-lingual retrieval resources, run cross-lingual retrieval baselines with three distinct multilingual embedding models (BGE-M3, multilingual-E5-large, and Qwen3-Embedding-4B), and analyze slice-wise quality metadata and query-type-wise field metrics supporting the corpus’s use as a difficulty-aware benchmark. Through our corpus, we also find (1) a 27.8–41.5-point NDCG@10 drop from English to Nepali, (2) descriptions are 5–6× harder than titles, and (3) hard negatives are 2× stickier than random distractors.</abstract>
<identifier type="citekey">dahal-etal-2026-wincc</identifier>
<location>
<url>https://aclanthology.org/2026.wac-1.12/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>131</start>
<end>138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WiNCC: A Reproducible Pipeline for Constructing a Wikipedia-enriched Nepali Cross-lingual Corpus
%A Dahal, Ahrnish P.
%A Baranwal, Pushkar
%A Pundir, Amit
%A Jain Saxena, Geetika
%A Singh, Sanjeev
%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 dahal-etal-2026-wincc
%X WiNCC is a reproducible and automatic construction pipeline for building an English–Nepali cross-lingual retrieval corpus that is difficulty-aware, relying on public Wikipedia and Wikidata. Part 1 reproduces a CLIRMatrix-style baseline. Nepali Wikipedia was crawled, articles resolved to a Wikidata QID, then intersected with Wikidata sitelinks to obtain Nepali–English query pairs and the corresponding English document corpus. These were sampled into gold pairs and padded with random English distractors to form a document baseline corpus. Part 2 adds a data-enrichment stage to Part 1 with multi-query, class-matched hard negatives. We compare the produced corpus against existing cross-lingual retrieval resources, run cross-lingual retrieval baselines with three distinct multilingual embedding models (BGE-M3, multilingual-E5-large, and Qwen3-Embedding-4B), and analyze slice-wise quality metadata and query-type-wise field metrics supporting the corpus’s use as a difficulty-aware benchmark. Through our corpus, we also find (1) a 27.8–41.5-point NDCG@10 drop from English to Nepali, (2) descriptions are 5–6× harder than titles, and (3) hard negatives are 2× stickier than random distractors.
%U https://aclanthology.org/2026.wac-1.12/
%P 131-138
Markdown (Informal)
[WiNCC: A Reproducible Pipeline for Constructing a Wikipedia-enriched Nepali Cross-lingual Corpus](https://aclanthology.org/2026.wac-1.12/) (Dahal et al., WAC 2026)
ACL