@inproceedings{huzaifah-etal-2024-evaluating,
title = "Evaluating Code-Switching Translation with Large Language Models",
author = "Huzaifah, Muhammad and
Zheng, Weihua and
Chanpaisit, Nattapol and
Wu, Kui",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.565",
pages = "6381--6394",
abstract = "Recent advances in large language models (LLMs) have shown they can match or surpass finetuned models on many natural language processing tasks. Currently, more studies are being carried out to assess whether this performance carries over across different languages. In this paper, we present a thorough evaluation of LLMs for the less well-researched code-switching translation setting, where inputs include a mixture of different languages. We benchmark the performance of six state-of-the-art LLMs across seven datasets, with GPT-4 and GPT-3.5 displaying strong ability relative to supervised translation models and commercial engines. GPT-4 was also found to be particularly robust against different code-switching conditions. Several methods to further improve code-switching translation are proposed including leveraging in-context learning and pivot translation. Through our code-switching experiments, we argue that LLMs show promising ability for cross-lingual understanding.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huzaifah-etal-2024-evaluating">
<titleInfo>
<title>Evaluating Code-Switching Translation with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Huzaifah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weihua</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nattapol</namePart>
<namePart type="family">Chanpaisit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kui</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</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">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in large language models (LLMs) have shown they can match or surpass finetuned models on many natural language processing tasks. Currently, more studies are being carried out to assess whether this performance carries over across different languages. In this paper, we present a thorough evaluation of LLMs for the less well-researched code-switching translation setting, where inputs include a mixture of different languages. We benchmark the performance of six state-of-the-art LLMs across seven datasets, with GPT-4 and GPT-3.5 displaying strong ability relative to supervised translation models and commercial engines. GPT-4 was also found to be particularly robust against different code-switching conditions. Several methods to further improve code-switching translation are proposed including leveraging in-context learning and pivot translation. Through our code-switching experiments, we argue that LLMs show promising ability for cross-lingual understanding.</abstract>
<identifier type="citekey">huzaifah-etal-2024-evaluating</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.565</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6381</start>
<end>6394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Code-Switching Translation with Large Language Models
%A Huzaifah, Muhammad
%A Zheng, Weihua
%A Chanpaisit, Nattapol
%A Wu, Kui
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F huzaifah-etal-2024-evaluating
%X Recent advances in large language models (LLMs) have shown they can match or surpass finetuned models on many natural language processing tasks. Currently, more studies are being carried out to assess whether this performance carries over across different languages. In this paper, we present a thorough evaluation of LLMs for the less well-researched code-switching translation setting, where inputs include a mixture of different languages. We benchmark the performance of six state-of-the-art LLMs across seven datasets, with GPT-4 and GPT-3.5 displaying strong ability relative to supervised translation models and commercial engines. GPT-4 was also found to be particularly robust against different code-switching conditions. Several methods to further improve code-switching translation are proposed including leveraging in-context learning and pivot translation. Through our code-switching experiments, we argue that LLMs show promising ability for cross-lingual understanding.
%U https://aclanthology.org/2024.lrec-main.565
%P 6381-6394
Markdown (Informal)
[Evaluating Code-Switching Translation with Large Language Models](https://aclanthology.org/2024.lrec-main.565) (Huzaifah et al., LREC-COLING 2024)
ACL
- Muhammad Huzaifah, Weihua Zheng, Nattapol Chanpaisit, and Kui Wu. 2024. Evaluating Code-Switching Translation with Large Language Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 6381–6394, Torino, Italia. ELRA and ICCL.