@inproceedings{kallur-anami-2025-word,
title = "A Word-Splitting Approach to {K}annada {S}anskrit Sandhi Words Useful in Effective {E}nglish Translation",
author = "Kallur, Shanta and
Anami, Basavaraj S.",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.34/",
pages = "579--588",
ISBN = "979-8-89176-303-6",
abstract = "Natural Language Processing is a branch of artificial intelligence that enables man- machine interactions through regional languages. In Kannada, there are two types of Sandhi: Kannada Sandhi and Sanskrit Sandhi. A morph-phonemic word ``Sandhi'' is created when two words or distinct morphemes are joined or combined. Conversely, Sandhi word splitting reverses this process. Rules governing Sandhi exist across all the Dravidian languages. A rule-based method has been developed to split Sanskrit Sandhi words into their components within Kannada sentences. Once the Sanskrit Sandhi (SS) words are split, the type of Sandhi is also identified, facilitating accurate translation of the Sanskrit Sandhi words into English. This paper discusses seven types of SS words: SavarNadeergha, YaN, GuNa, Vruddhi, Jatva, Shchutva and Anunasika Sandhi. The identified split points adhere precisely to Sandhi rules. A dataset of 4900 SanskritSandhi words found in Kannada sentences was used to evaluate the proposed method, which achieved an accuracy of 90.03{\%} for Sanskrit Sandhi Identification and 85.87{\%} for reliable English Translation. This work has potential applications in other Dravidian languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kallur-anami-2025-word">
<titleInfo>
<title>A Word-Splitting Approach to Kannada Sanskrit Sandhi Words Useful in Effective English Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shanta</namePart>
<namePart type="family">Kallur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Basavaraj</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Anami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Natural Language Processing is a branch of artificial intelligence that enables man- machine interactions through regional languages. In Kannada, there are two types of Sandhi: Kannada Sandhi and Sanskrit Sandhi. A morph-phonemic word “Sandhi” is created when two words or distinct morphemes are joined or combined. Conversely, Sandhi word splitting reverses this process. Rules governing Sandhi exist across all the Dravidian languages. A rule-based method has been developed to split Sanskrit Sandhi words into their components within Kannada sentences. Once the Sanskrit Sandhi (SS) words are split, the type of Sandhi is also identified, facilitating accurate translation of the Sanskrit Sandhi words into English. This paper discusses seven types of SS words: SavarNadeergha, YaN, GuNa, Vruddhi, Jatva, Shchutva and Anunasika Sandhi. The identified split points adhere precisely to Sandhi rules. A dataset of 4900 SanskritSandhi words found in Kannada sentences was used to evaluate the proposed method, which achieved an accuracy of 90.03% for Sanskrit Sandhi Identification and 85.87% for reliable English Translation. This work has potential applications in other Dravidian languages.</abstract>
<identifier type="citekey">kallur-anami-2025-word</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.34/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>579</start>
<end>588</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Word-Splitting Approach to Kannada Sanskrit Sandhi Words Useful in Effective English Translation
%A Kallur, Shanta
%A Anami, Basavaraj S.
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F kallur-anami-2025-word
%X Natural Language Processing is a branch of artificial intelligence that enables man- machine interactions through regional languages. In Kannada, there are two types of Sandhi: Kannada Sandhi and Sanskrit Sandhi. A morph-phonemic word “Sandhi” is created when two words or distinct morphemes are joined or combined. Conversely, Sandhi word splitting reverses this process. Rules governing Sandhi exist across all the Dravidian languages. A rule-based method has been developed to split Sanskrit Sandhi words into their components within Kannada sentences. Once the Sanskrit Sandhi (SS) words are split, the type of Sandhi is also identified, facilitating accurate translation of the Sanskrit Sandhi words into English. This paper discusses seven types of SS words: SavarNadeergha, YaN, GuNa, Vruddhi, Jatva, Shchutva and Anunasika Sandhi. The identified split points adhere precisely to Sandhi rules. A dataset of 4900 SanskritSandhi words found in Kannada sentences was used to evaluate the proposed method, which achieved an accuracy of 90.03% for Sanskrit Sandhi Identification and 85.87% for reliable English Translation. This work has potential applications in other Dravidian languages.
%U https://aclanthology.org/2025.findings-ijcnlp.34/
%P 579-588
Markdown (Informal)
[A Word-Splitting Approach to Kannada Sanskrit Sandhi Words Useful in Effective English Translation](https://aclanthology.org/2025.findings-ijcnlp.34/) (Kallur & Anami, Findings 2025)
ACL