@inproceedings{mujadia-etal-2024-assessing,
title = "Assessing Translation Capabilities of Large Language Models involving {E}nglish and {I}ndian Languages",
author = "Mujadia, Vandan and
Urlana, Ashok and
Bhaskar, Yash and
Aditya Pavani, Penumalla and
Shravya, Kukkapalli and
Krishnamurthy, Parameswari and
Sharma, Dipti",
editor = "Scarton, Carolina and
Prescott, Charlotte and
Bayliss, Chris and
Oakley, Chris and
Wright, Joanna and
Wrigley, Stuart and
Song, Xingyi and
Gow-Smith, Edward and
Bawden, Rachel and
S{\'a}nchez-Cartagena, V{\'\i}ctor M and
Cadwell, Patrick and
Lapshinova-Koltunski, Ekaterina and
Cabarr{\~a}o, Vera and
Chatzitheodorou, Konstantinos and
Nurminen, Mary and
Kanojia, Diptesh and
Moniz, Helena",
booktitle = "Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)",
month = jun,
year = "2024",
address = "Sheffield, UK",
publisher = "European Association for Machine Translation (EAMT)",
url = "https://aclanthology.org/2024.eamt-1.19",
pages = "207--228",
abstract = "Generative Large Language Models (LLMs) have achieved remarkable advances in various NLP tasks. In this work, our aim is to explore the multilingual capabilities of large language models by using machine translation as a task involving English and 22 Indian languages. We first investigate the translation capabilities of raw large-language models, followed by exploring the in-context learning capabilities of the same raw models. We fine-tune these large language models using parameter-efficient fine-tuning methods such as LoRA and additionally with full fine-tuning. Through our study, we have identified the model that performs best among the large language models available for the translation task.Our results demonstrate significant progress, with average BLEU scores of 13.42, 15.93, 12.13, 12.30, and 12.07, as well as chrF scores of 43.98, 46.99, 42.55, 42.42, and 45.39, respectively, using two-stage fine-tuned LLaMA-13b for English to Indian languages on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest, and newstest2019 testsets. Similarly, for Indian languages to English, we achieved average BLEU scores of 14.03, 16.65, 16.17, 15.35 and 12.55 along with chrF scores of 36.71, 40.44, 40.26, 39.51, and 36.20, respectively, using fine-tuned LLaMA-13b on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest and newstest2019 testsets. Overall, our findings highlight the potential and strength of large language models for machine translation capabilities, including languages that are currently underrepresented in LLMs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mujadia-etal-2024-assessing">
<titleInfo>
<title>Assessing Translation Capabilities of Large Language Models involving English and Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vandan</namePart>
<namePart type="family">Mujadia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashok</namePart>
<namePart type="family">Urlana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yash</namePart>
<namePart type="family">Bhaskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Penumalla</namePart>
<namePart type="family">Aditya Pavani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kukkapalli</namePart>
<namePart type="family">Shravya</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>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charlotte</namePart>
<namePart type="family">Prescott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Bayliss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Oakley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Wright</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stuart</namePart>
<namePart type="family">Wrigley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingyi</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Gow-Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Víctor</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Sánchez-Cartagena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Cadwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Lapshinova-Koltunski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Cabarrão</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantinos</namePart>
<namePart type="family">Chatzitheodorou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diptesh</namePart>
<namePart type="family">Kanojia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation (EAMT)</publisher>
<place>
<placeTerm type="text">Sheffield, UK</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generative Large Language Models (LLMs) have achieved remarkable advances in various NLP tasks. In this work, our aim is to explore the multilingual capabilities of large language models by using machine translation as a task involving English and 22 Indian languages. We first investigate the translation capabilities of raw large-language models, followed by exploring the in-context learning capabilities of the same raw models. We fine-tune these large language models using parameter-efficient fine-tuning methods such as LoRA and additionally with full fine-tuning. Through our study, we have identified the model that performs best among the large language models available for the translation task.Our results demonstrate significant progress, with average BLEU scores of 13.42, 15.93, 12.13, 12.30, and 12.07, as well as chrF scores of 43.98, 46.99, 42.55, 42.42, and 45.39, respectively, using two-stage fine-tuned LLaMA-13b for English to Indian languages on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest, and newstest2019 testsets. Similarly, for Indian languages to English, we achieved average BLEU scores of 14.03, 16.65, 16.17, 15.35 and 12.55 along with chrF scores of 36.71, 40.44, 40.26, 39.51, and 36.20, respectively, using fine-tuned LLaMA-13b on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest and newstest2019 testsets. Overall, our findings highlight the potential and strength of large language models for machine translation capabilities, including languages that are currently underrepresented in LLMs.</abstract>
<identifier type="citekey">mujadia-etal-2024-assessing</identifier>
<location>
<url>https://aclanthology.org/2024.eamt-1.19</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>207</start>
<end>228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessing Translation Capabilities of Large Language Models involving English and Indian Languages
%A Mujadia, Vandan
%A Urlana, Ashok
%A Bhaskar, Yash
%A Aditya Pavani, Penumalla
%A Shravya, Kukkapalli
%A Krishnamurthy, Parameswari
%A Sharma, Dipti
%Y Scarton, Carolina
%Y Prescott, Charlotte
%Y Bayliss, Chris
%Y Oakley, Chris
%Y Wright, Joanna
%Y Wrigley, Stuart
%Y Song, Xingyi
%Y Gow-Smith, Edward
%Y Bawden, Rachel
%Y Sánchez-Cartagena, Víctor M.
%Y Cadwell, Patrick
%Y Lapshinova-Koltunski, Ekaterina
%Y Cabarrão, Vera
%Y Chatzitheodorou, Konstantinos
%Y Nurminen, Mary
%Y Kanojia, Diptesh
%Y Moniz, Helena
%S Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)
%D 2024
%8 June
%I European Association for Machine Translation (EAMT)
%C Sheffield, UK
%F mujadia-etal-2024-assessing
%X Generative Large Language Models (LLMs) have achieved remarkable advances in various NLP tasks. In this work, our aim is to explore the multilingual capabilities of large language models by using machine translation as a task involving English and 22 Indian languages. We first investigate the translation capabilities of raw large-language models, followed by exploring the in-context learning capabilities of the same raw models. We fine-tune these large language models using parameter-efficient fine-tuning methods such as LoRA and additionally with full fine-tuning. Through our study, we have identified the model that performs best among the large language models available for the translation task.Our results demonstrate significant progress, with average BLEU scores of 13.42, 15.93, 12.13, 12.30, and 12.07, as well as chrF scores of 43.98, 46.99, 42.55, 42.42, and 45.39, respectively, using two-stage fine-tuned LLaMA-13b for English to Indian languages on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest, and newstest2019 testsets. Similarly, for Indian languages to English, we achieved average BLEU scores of 14.03, 16.65, 16.17, 15.35 and 12.55 along with chrF scores of 36.71, 40.44, 40.26, 39.51, and 36.20, respectively, using fine-tuned LLaMA-13b on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest and newstest2019 testsets. Overall, our findings highlight the potential and strength of large language models for machine translation capabilities, including languages that are currently underrepresented in LLMs.
%U https://aclanthology.org/2024.eamt-1.19
%P 207-228
Markdown (Informal)
[Assessing Translation Capabilities of Large Language Models involving English and Indian Languages](https://aclanthology.org/2024.eamt-1.19) (Mujadia et al., EAMT 2024)
ACL