@inproceedings{jayatilleke-etal-2026-sidiac,
title = "{S}i{D}ia{C}-v.2.0: {S}inhala Diachronic Corpus Version 2.0",
author = "Jayatilleke, Nevidu and
de Silva, Nisansa and
Sooriya-Arachchi, Uthpala Nimanthi and
Kulathilaka, Gagani Kasundhi and
Safrullah, Azra and
Sofalas, Johan Nevin",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.537/",
doi = "10.63317/2ybff4o55vrq",
pages = "6740--6763",
abstract = "SiDiaC-v.2.0 is the largest comprehensive Sinhala Diachronic Corpus to date, covering a period from 1800 CE to 1955 CE in terms of publication dates, and a historical span from the 5th to the 20th century CE in terms of written dates. The corpus consists of 244k words across 185 literary works that underwent thorough filtering, preprocessing, and copyright compliance checks, followed by extensive post-processing. Additionally, a subset of 59 documents totalling 70k words was annotated based on their written dates. Texts from the National Library of Sri Lanka were selected from the SiDiaC-v.1.0 non-filtered list, which was digitised using Google Document AI OCR. This was followed by post-processing to correct formatting issues, address code-mixing, include special tokens, and fix malformed tokens. The construction of SiDiaC-v.2.0 was informed by practices from other corpora, such as FarPaHC, SiDiaC-v.1.0, and CCOHA. This was particularly relevant for syntactic annotation and text normalisation strategies, given the shared characteristics of low-resource language status between Faroese and the similar cleaning strategies utilised in CCOHA. This corpus is categorised into two layers based on genres: primary and secondary. The primary categorisation is binary, assigning each book to either Non-Fiction or Fiction. The secondary categorisation is more detailed, grouping texts under specific genres such as Religious, History, Poetry, Language, and Medical. Despite facing challenges due to limited resources, SiDiaC-v.2.0 serves as a comprehensive resource for Sinhala NLP, building upon the work previously done in SiDiaC-v.1.0."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jayatilleke-etal-2026-sidiac">
<titleInfo>
<title>SiDiaC-v.2.0: Sinhala Diachronic Corpus Version 2.0</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nevidu</namePart>
<namePart type="family">Jayatilleke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nisansa</namePart>
<namePart type="family">de Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uthpala</namePart>
<namePart type="given">Nimanthi</namePart>
<namePart type="family">Sooriya-Arachchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gagani</namePart>
<namePart type="given">Kasundhi</namePart>
<namePart type="family">Kulathilaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azra</namePart>
<namePart type="family">Safrullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johan</namePart>
<namePart type="given">Nevin</namePart>
<namePart type="family">Sofalas</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 Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>SiDiaC-v.2.0 is the largest comprehensive Sinhala Diachronic Corpus to date, covering a period from 1800 CE to 1955 CE in terms of publication dates, and a historical span from the 5th to the 20th century CE in terms of written dates. The corpus consists of 244k words across 185 literary works that underwent thorough filtering, preprocessing, and copyright compliance checks, followed by extensive post-processing. Additionally, a subset of 59 documents totalling 70k words was annotated based on their written dates. Texts from the National Library of Sri Lanka were selected from the SiDiaC-v.1.0 non-filtered list, which was digitised using Google Document AI OCR. This was followed by post-processing to correct formatting issues, address code-mixing, include special tokens, and fix malformed tokens. The construction of SiDiaC-v.2.0 was informed by practices from other corpora, such as FarPaHC, SiDiaC-v.1.0, and CCOHA. This was particularly relevant for syntactic annotation and text normalisation strategies, given the shared characteristics of low-resource language status between Faroese and the similar cleaning strategies utilised in CCOHA. This corpus is categorised into two layers based on genres: primary and secondary. The primary categorisation is binary, assigning each book to either Non-Fiction or Fiction. The secondary categorisation is more detailed, grouping texts under specific genres such as Religious, History, Poetry, Language, and Medical. Despite facing challenges due to limited resources, SiDiaC-v.2.0 serves as a comprehensive resource for Sinhala NLP, building upon the work previously done in SiDiaC-v.1.0.</abstract>
<identifier type="citekey">jayatilleke-etal-2026-sidiac</identifier>
<identifier type="doi">10.63317/2ybff4o55vrq</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.537/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>6740</start>
<end>6763</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SiDiaC-v.2.0: Sinhala Diachronic Corpus Version 2.0
%A Jayatilleke, Nevidu
%A de Silva, Nisansa
%A Sooriya-Arachchi, Uthpala Nimanthi
%A Kulathilaka, Gagani Kasundhi
%A Safrullah, Azra
%A Sofalas, Johan Nevin
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F jayatilleke-etal-2026-sidiac
%X SiDiaC-v.2.0 is the largest comprehensive Sinhala Diachronic Corpus to date, covering a period from 1800 CE to 1955 CE in terms of publication dates, and a historical span from the 5th to the 20th century CE in terms of written dates. The corpus consists of 244k words across 185 literary works that underwent thorough filtering, preprocessing, and copyright compliance checks, followed by extensive post-processing. Additionally, a subset of 59 documents totalling 70k words was annotated based on their written dates. Texts from the National Library of Sri Lanka were selected from the SiDiaC-v.1.0 non-filtered list, which was digitised using Google Document AI OCR. This was followed by post-processing to correct formatting issues, address code-mixing, include special tokens, and fix malformed tokens. The construction of SiDiaC-v.2.0 was informed by practices from other corpora, such as FarPaHC, SiDiaC-v.1.0, and CCOHA. This was particularly relevant for syntactic annotation and text normalisation strategies, given the shared characteristics of low-resource language status between Faroese and the similar cleaning strategies utilised in CCOHA. This corpus is categorised into two layers based on genres: primary and secondary. The primary categorisation is binary, assigning each book to either Non-Fiction or Fiction. The secondary categorisation is more detailed, grouping texts under specific genres such as Religious, History, Poetry, Language, and Medical. Despite facing challenges due to limited resources, SiDiaC-v.2.0 serves as a comprehensive resource for Sinhala NLP, building upon the work previously done in SiDiaC-v.1.0.
%R 10.63317/2ybff4o55vrq
%U https://aclanthology.org/2026.lrec-1.537/
%U https://doi.org/10.63317/2ybff4o55vrq
%P 6740-6763
Markdown (Informal)
[SiDiaC-v.2.0: Sinhala Diachronic Corpus Version 2.0](https://aclanthology.org/2026.lrec-1.537/) (Jayatilleke et al., LREC 2026)
ACL
- Nevidu Jayatilleke, Nisansa de Silva, Uthpala Nimanthi Sooriya-Arachchi, Gagani Kasundhi Kulathilaka, Azra Safrullah, and Johan Nevin Sofalas. 2026. SiDiaC-v.2.0: Sinhala Diachronic Corpus Version 2.0. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 6740–6763, Palma de Mallorca, Spain. ELRA Language Resource Association.