@inproceedings{dabre-etal-2024-machine,
title = "Machine Translation Of {M}arathi Dialects: A Case Study Of Kadodi",
author = "Dabre, Raj and
Dabre, Mary and
Pereira, Teresa",
editor = "Nakazawa, Toshiaki and
Goto, Isao",
booktitle = "Proceedings of the Eleventh Workshop on Asian Translation (WAT 2024)",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wat-1.3",
pages = "36--44",
abstract = "While Marathi is considered as a low- to middle-resource language, its 42 dialects have mostly been ignored, mainly because these dialects are mostly spoken and rarely written, making them extremely low-resource. In this paper we explore the machine translation (MT) of Kadodi, also known as Samvedi, which is a dialect of Marathi. We first discuss the Kadodi dialect, highlighting the differences from the standard dialect, followed by presenting a manually curated dataset called Suman consisting of a trilingual Kadodi-Marathi-English dictionary of 949 entries and 942 simple sentence triples and idioms created by native Kadodi speakers. We then evaluate 3 existing large language models (LLMs) supporting Marathi, namely Gemma-2-9b, Sarvam-2b-0.5 and LLaMa-3.1-8b, in few-shot prompting style to determine their efficacy for translation involving Kadodi. We observe that these models exhibit rather lackluster performance in handling Kadodi even for simple sentences, indicating a dire situation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dabre-etal-2024-machine">
<titleInfo>
<title>Machine Translation Of Marathi Dialects: A Case Study Of Kadodi</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teresa</namePart>
<namePart type="family">Pereira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eleventh Workshop on Asian Translation (WAT 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isao</namePart>
<namePart type="family">Goto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While Marathi is considered as a low- to middle-resource language, its 42 dialects have mostly been ignored, mainly because these dialects are mostly spoken and rarely written, making them extremely low-resource. In this paper we explore the machine translation (MT) of Kadodi, also known as Samvedi, which is a dialect of Marathi. We first discuss the Kadodi dialect, highlighting the differences from the standard dialect, followed by presenting a manually curated dataset called Suman consisting of a trilingual Kadodi-Marathi-English dictionary of 949 entries and 942 simple sentence triples and idioms created by native Kadodi speakers. We then evaluate 3 existing large language models (LLMs) supporting Marathi, namely Gemma-2-9b, Sarvam-2b-0.5 and LLaMa-3.1-8b, in few-shot prompting style to determine their efficacy for translation involving Kadodi. We observe that these models exhibit rather lackluster performance in handling Kadodi even for simple sentences, indicating a dire situation.</abstract>
<identifier type="citekey">dabre-etal-2024-machine</identifier>
<location>
<url>https://aclanthology.org/2024.wat-1.3</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>36</start>
<end>44</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Translation Of Marathi Dialects: A Case Study Of Kadodi
%A Dabre, Raj
%A Dabre, Mary
%A Pereira, Teresa
%Y Nakazawa, Toshiaki
%Y Goto, Isao
%S Proceedings of the Eleventh Workshop on Asian Translation (WAT 2024)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F dabre-etal-2024-machine
%X While Marathi is considered as a low- to middle-resource language, its 42 dialects have mostly been ignored, mainly because these dialects are mostly spoken and rarely written, making them extremely low-resource. In this paper we explore the machine translation (MT) of Kadodi, also known as Samvedi, which is a dialect of Marathi. We first discuss the Kadodi dialect, highlighting the differences from the standard dialect, followed by presenting a manually curated dataset called Suman consisting of a trilingual Kadodi-Marathi-English dictionary of 949 entries and 942 simple sentence triples and idioms created by native Kadodi speakers. We then evaluate 3 existing large language models (LLMs) supporting Marathi, namely Gemma-2-9b, Sarvam-2b-0.5 and LLaMa-3.1-8b, in few-shot prompting style to determine their efficacy for translation involving Kadodi. We observe that these models exhibit rather lackluster performance in handling Kadodi even for simple sentences, indicating a dire situation.
%U https://aclanthology.org/2024.wat-1.3
%P 36-44
Markdown (Informal)
[Machine Translation Of Marathi Dialects: A Case Study Of Kadodi](https://aclanthology.org/2024.wat-1.3) (Dabre et al., WAT 2024)
ACL