@inproceedings{dasari-etal-2025-sandhi,
title = "Sandhi Splitting in {T}amil and {T}elugu: A Sequence-to-Sequence Approach Leveraging Transformer Models",
author = "Dasari, Priyanka and
Sohan Gupta, Mupparapu and
Vuppala, Nagaraju and
Mishra, Pruthwik and
Krishnamurthy, Parameswari",
editor = "Sarveswaran, Kengatharaiyer and
Vaidya, Ashwini and
Krishna Bal, Bal and
Shams, Sana and
Thapa, Surendrabikram",
booktitle = "Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2025.chipsal-1.9/",
pages = "93--103",
abstract = "Dravidian languages like Tamil and Telugu are agglutinative languages, they form wordforms by combining two or more elements into a single string with morpho-phonemic changes at the point of concatenation, known as sandhi. This linguistic feature adds complexity to automatic language processing, making the pre-processing of sandhi words essential for NLP applications. We developed extensive sandhi-annotated corpora of 15K for Telugu and Tamil, focusing on the systematic application of sandhi rules which explains the word formation patterns by showing how lexical and functional categories combine to create composite non-compound words. We implemented compact sequence-to-sequence transformer networks for the automatic sandhi processing. To evaluate our models, we manually annotated Telugu and Tamil IN22-Conv Benchmark datasets with sandhi annotations. Our experiments aim to enhance the language processing tasks like machine translation in morphologically rich languages."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dasari-etal-2025-sandhi">
<titleInfo>
<title>Sandhi Splitting in Tamil and Telugu: A Sequence-to-Sequence Approach Leveraging Transformer Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Priyanka</namePart>
<namePart type="family">Dasari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mupparapu</namePart>
<namePart type="family">Sohan Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nagaraju</namePart>
<namePart type="family">Vuppala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pruthwik</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="family">Krishna Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sana</namePart>
<namePart type="family">Shams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dravidian languages like Tamil and Telugu are agglutinative languages, they form wordforms by combining two or more elements into a single string with morpho-phonemic changes at the point of concatenation, known as sandhi. This linguistic feature adds complexity to automatic language processing, making the pre-processing of sandhi words essential for NLP applications. We developed extensive sandhi-annotated corpora of 15K for Telugu and Tamil, focusing on the systematic application of sandhi rules which explains the word formation patterns by showing how lexical and functional categories combine to create composite non-compound words. We implemented compact sequence-to-sequence transformer networks for the automatic sandhi processing. To evaluate our models, we manually annotated Telugu and Tamil IN22-Conv Benchmark datasets with sandhi annotations. Our experiments aim to enhance the language processing tasks like machine translation in morphologically rich languages.</abstract>
<identifier type="citekey">dasari-etal-2025-sandhi</identifier>
<location>
<url>https://aclanthology.org/2025.chipsal-1.9/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>93</start>
<end>103</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sandhi Splitting in Tamil and Telugu: A Sequence-to-Sequence Approach Leveraging Transformer Models
%A Dasari, Priyanka
%A Sohan Gupta, Mupparapu
%A Vuppala, Nagaraju
%A Mishra, Pruthwik
%A Krishnamurthy, Parameswari
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%Y Krishna Bal, Bal
%Y Shams, Sana
%Y Thapa, Surendrabikram
%S Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)
%D 2025
%8 January
%I International Committee on Computational Linguistics
%C Abu Dhabi, UAE
%F dasari-etal-2025-sandhi
%X Dravidian languages like Tamil and Telugu are agglutinative languages, they form wordforms by combining two or more elements into a single string with morpho-phonemic changes at the point of concatenation, known as sandhi. This linguistic feature adds complexity to automatic language processing, making the pre-processing of sandhi words essential for NLP applications. We developed extensive sandhi-annotated corpora of 15K for Telugu and Tamil, focusing on the systematic application of sandhi rules which explains the word formation patterns by showing how lexical and functional categories combine to create composite non-compound words. We implemented compact sequence-to-sequence transformer networks for the automatic sandhi processing. To evaluate our models, we manually annotated Telugu and Tamil IN22-Conv Benchmark datasets with sandhi annotations. Our experiments aim to enhance the language processing tasks like machine translation in morphologically rich languages.
%U https://aclanthology.org/2025.chipsal-1.9/
%P 93-103
Markdown (Informal)
[Sandhi Splitting in Tamil and Telugu: A Sequence-to-Sequence Approach Leveraging Transformer Models](https://aclanthology.org/2025.chipsal-1.9/) (Dasari et al., CHiPSAL 2025)
ACL