@inproceedings{vandan-etal-2023-towards,
title = "Towards Large Language Model driven Reference-less Translation Evaluation for {E}nglish and {I}ndian Language",
author = "Vandan, Mujadia and
Pruthwik, Mishra and
Arafat, Ahsan and
Dipti, M. Sharma",
editor = "Jyoti, D. Pawar and
Sobha, Lalitha Devi",
booktitle = "Proceedings of the 20th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2023",
address = "Goa University, Goa, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2023.icon-1.28",
pages = "357--369",
abstract = "With the primary focus on evaluating the effectiveness of large language models for automatic reference-less translation assessment, this work presents our experiments on mimicking human direct assessment to evaluate the quality of translations in English and Indian languages. We constructed a translation evaluation task where we performed zero-shot learning, in-context example-driven learning, and fine-tuning of large language models to provide a score out of 100, where 100 represents a perfect translation and 1 represents a poor translation. We compared the performance of our trained systems with existing methods such as COMET, BERT-Scorer, and LABSE, and found that the LLM-based evaluator (LLaMA2-13B) achieves a comparable or higher overall correlation with human judgments for the considered Indian language pairs (Refer figure 1).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vandan-etal-2023-towards">
<titleInfo>
<title>Towards Large Language Model driven Reference-less Translation Evaluation for English and Indian Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mujadia</namePart>
<namePart type="family">Vandan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mishra</namePart>
<namePart type="family">Pruthwik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahsan</namePart>
<namePart type="family">Arafat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M</namePart>
<namePart type="given">Sharma</namePart>
<namePart type="family">Dipti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">D</namePart>
<namePart type="given">Pawar</namePart>
<namePart type="family">Jyoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lalitha</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Sobha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Goa University, Goa, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the primary focus on evaluating the effectiveness of large language models for automatic reference-less translation assessment, this work presents our experiments on mimicking human direct assessment to evaluate the quality of translations in English and Indian languages. We constructed a translation evaluation task where we performed zero-shot learning, in-context example-driven learning, and fine-tuning of large language models to provide a score out of 100, where 100 represents a perfect translation and 1 represents a poor translation. We compared the performance of our trained systems with existing methods such as COMET, BERT-Scorer, and LABSE, and found that the LLM-based evaluator (LLaMA2-13B) achieves a comparable or higher overall correlation with human judgments for the considered Indian language pairs (Refer figure 1).</abstract>
<identifier type="citekey">vandan-etal-2023-towards</identifier>
<location>
<url>https://aclanthology.org/2023.icon-1.28</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>357</start>
<end>369</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Large Language Model driven Reference-less Translation Evaluation for English and Indian Language
%A Vandan, Mujadia
%A Pruthwik, Mishra
%A Arafat, Ahsan
%A Dipti, M. Sharma
%Y Jyoti, D. Pawar
%Y Sobha, Lalitha Devi
%S Proceedings of the 20th International Conference on Natural Language Processing (ICON)
%D 2023
%8 December
%I NLP Association of India (NLPAI)
%C Goa University, Goa, India
%F vandan-etal-2023-towards
%X With the primary focus on evaluating the effectiveness of large language models for automatic reference-less translation assessment, this work presents our experiments on mimicking human direct assessment to evaluate the quality of translations in English and Indian languages. We constructed a translation evaluation task where we performed zero-shot learning, in-context example-driven learning, and fine-tuning of large language models to provide a score out of 100, where 100 represents a perfect translation and 1 represents a poor translation. We compared the performance of our trained systems with existing methods such as COMET, BERT-Scorer, and LABSE, and found that the LLM-based evaluator (LLaMA2-13B) achieves a comparable or higher overall correlation with human judgments for the considered Indian language pairs (Refer figure 1).
%U https://aclanthology.org/2023.icon-1.28
%P 357-369
Markdown (Informal)
[Towards Large Language Model driven Reference-less Translation Evaluation for English and Indian Language](https://aclanthology.org/2023.icon-1.28) (Vandan et al., ICON 2023)
ACL