@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",
abstract = "Language models have achieved state-of-the-art performance across many natural language processing (NLP) tasks, but low-resource languages remain underrepresented due to limited pre-training data and evaluation benchmarks. While recent efforts have introduced corpora, models, and benchmarks for such languages, most focus on a single language in isolation. This is particularly limiting in multilingual countries such as Sri Lanka, where the lack of comparable multilingual resources hinders the development and fair evaluation of models across languages. To address this gap, we introduce CeyNews, the largest trilingual news corpus for Sinhala, Tamil, and English. The dataset contains over 1.02 million articles (136 million tokens) collected between 2013 and 2026 from three news sources, with full article text and rich metadata. Using CeyNews, we develop three downstream tasks: news source identification, news category classification, and headline generation, and evaluate multilingual models across different learning settings. Our results demonstrate the challenges of applying multilingual models to these tasks, particularly for the headline generation task. CeyNews fills a major gap in Sri Lankan and South Asian language resources and is publicly released to support research in multilingual NLP, LLM adaptation, and digital humanities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sivakulasingam-etal-2026-ceynews">
<titleInfo>
<title>CeyNews: A Sri Lankan Trilingual News Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ajintha</namePart>
<namePart type="family">Sivakulasingam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</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>Language models have achieved state-of-the-art performance across many natural language processing (NLP) tasks, but low-resource languages remain underrepresented due to limited pre-training data and evaluation benchmarks. While recent efforts have introduced corpora, models, and benchmarks for such languages, most focus on a single language in isolation. This is particularly limiting in multilingual countries such as Sri Lanka, where the lack of comparable multilingual resources hinders the development and fair evaluation of models across languages. To address this gap, we introduce CeyNews, the largest trilingual news corpus for Sinhala, Tamil, and English. The dataset contains over 1.02 million articles (136 million tokens) collected between 2013 and 2026 from three news sources, with full article text and rich metadata. Using CeyNews, we develop three downstream tasks: news source identification, news category classification, and headline generation, and evaluate multilingual models across different learning settings. Our results demonstrate the challenges of applying multilingual models to these tasks, particularly for the headline generation task. CeyNews fills a major gap in Sri Lankan and South Asian language resources and is publicly released to support research in multilingual NLP, LLM adaptation, and digital humanities.</abstract>
<identifier type="citekey">sivakulasingam-etal-2026-ceynews</identifier>
<location>
<url>https://aclanthology.org/2026.wac-1.27/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>308</start>
<end>319</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CeyNews: A Sri Lankan Trilingual News Corpus
%A Sivakulasingam, Ajintha
%A Sarveswaran, Kengatharaiyer
%A Ranasinghe, Tharindu
%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 sivakulasingam-etal-2026-ceynews
%X Language models have achieved state-of-the-art performance across many natural language processing (NLP) tasks, but low-resource languages remain underrepresented due to limited pre-training data and evaluation benchmarks. While recent efforts have introduced corpora, models, and benchmarks for such languages, most focus on a single language in isolation. This is particularly limiting in multilingual countries such as Sri Lanka, where the lack of comparable multilingual resources hinders the development and fair evaluation of models across languages. To address this gap, we introduce CeyNews, the largest trilingual news corpus for Sinhala, Tamil, and English. The dataset contains over 1.02 million articles (136 million tokens) collected between 2013 and 2026 from three news sources, with full article text and rich metadata. Using CeyNews, we develop three downstream tasks: news source identification, news category classification, and headline generation, and evaluate multilingual models across different learning settings. Our results demonstrate the challenges of applying multilingual models to these tasks, particularly for the headline generation task. CeyNews fills a major gap in Sri Lankan and South Asian language resources and is publicly released to support research in multilingual NLP, LLM adaptation, and digital humanities.
%U https://aclanthology.org/2026.wac-1.27/
%P 308-319
Markdown (Informal)
[CeyNews: A Sri Lankan Trilingual News Corpus](https://aclanthology.org/2026.wac-1.27/) (Sivakulasingam et al., WAC 2026)
ACL
- Ajintha Sivakulasingam, Kengatharaiyer Sarveswaran, and Tharindu Ranasinghe. 2026. CeyNews: A Sri Lankan Trilingual News Corpus. In Proceedings of the 13th Web-as-Corpus Workshop, pages 308–319, Budapest, Hungary. Association for Computational Linguistics.