@inproceedings{guo-etal-2024-teaching-large,
title = "Teaching Large Language Models to Translate on Low-resource Languages with Textbook Prompting",
author = "Guo, Ping and
Ren, Yubing and
Hu, Yue and
Li, Yunpeng and
Zhang, Jiarui and
Zhang, Xingsheng and
Huang, Heyan",
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.1362",
pages = "15685--15697",
abstract = "Large Language Models (LLMs) have achieved impressive results in Machine Translation by simply following instructions, even without training on parallel data. However, LLMs still face challenges on low-resource languages due to the lack of pre-training data. In real-world situations, humans can become proficient in their native languages through abundant and meaningful social interactions and can also learn foreign languages effectively using well-organized textbooks. Drawing inspiration from human learning patterns, we introduce the Translate After LEarNing Textbook (TALENT) approach, which aims to enhance LLMs{'} ability to translate low-resource languages by learning from a textbook. TALENT follows a step-by-step process: (1) Creating a Textbook for low-resource languages. (2) Guiding LLMs to absorb the Textbook{'}s content for Syntax Patterns. (3) Enhancing translation by utilizing the Textbook and Syntax Patterns. We thoroughly assess TALENT{'}s performance using 112 low-resource languages from FLORES-200 with two LLMs: ChatGPT and BLOOMZ. Evaluation across three different metrics reveals that TALENT consistently enhances translation performance by 14.8{\%} compared to zero-shot baselines. Further analysis demonstrates that TALENT not only improves LLMs{'} comprehension of low-resource languages but also equips them with the knowledge needed to generate accurate and fluent sentences in these languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2024-teaching-large">
<titleInfo>
<title>Teaching Large Language Models to Translate on Low-resource Languages with Textbook Prompting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubing</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunpeng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiarui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingsheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heyan</namePart>
<namePart type="family">Huang</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>Large Language Models (LLMs) have achieved impressive results in Machine Translation by simply following instructions, even without training on parallel data. However, LLMs still face challenges on low-resource languages due to the lack of pre-training data. In real-world situations, humans can become proficient in their native languages through abundant and meaningful social interactions and can also learn foreign languages effectively using well-organized textbooks. Drawing inspiration from human learning patterns, we introduce the Translate After LEarNing Textbook (TALENT) approach, which aims to enhance LLMs’ ability to translate low-resource languages by learning from a textbook. TALENT follows a step-by-step process: (1) Creating a Textbook for low-resource languages. (2) Guiding LLMs to absorb the Textbook’s content for Syntax Patterns. (3) Enhancing translation by utilizing the Textbook and Syntax Patterns. We thoroughly assess TALENT’s performance using 112 low-resource languages from FLORES-200 with two LLMs: ChatGPT and BLOOMZ. Evaluation across three different metrics reveals that TALENT consistently enhances translation performance by 14.8% compared to zero-shot baselines. Further analysis demonstrates that TALENT not only improves LLMs’ comprehension of low-resource languages but also equips them with the knowledge needed to generate accurate and fluent sentences in these languages.</abstract>
<identifier type="citekey">guo-etal-2024-teaching-large</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1362</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15685</start>
<end>15697</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Teaching Large Language Models to Translate on Low-resource Languages with Textbook Prompting
%A Guo, Ping
%A Ren, Yubing
%A Hu, Yue
%A Li, Yunpeng
%A Zhang, Jiarui
%A Zhang, Xingsheng
%A Huang, Heyan
%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 guo-etal-2024-teaching-large
%X Large Language Models (LLMs) have achieved impressive results in Machine Translation by simply following instructions, even without training on parallel data. However, LLMs still face challenges on low-resource languages due to the lack of pre-training data. In real-world situations, humans can become proficient in their native languages through abundant and meaningful social interactions and can also learn foreign languages effectively using well-organized textbooks. Drawing inspiration from human learning patterns, we introduce the Translate After LEarNing Textbook (TALENT) approach, which aims to enhance LLMs’ ability to translate low-resource languages by learning from a textbook. TALENT follows a step-by-step process: (1) Creating a Textbook for low-resource languages. (2) Guiding LLMs to absorb the Textbook’s content for Syntax Patterns. (3) Enhancing translation by utilizing the Textbook and Syntax Patterns. We thoroughly assess TALENT’s performance using 112 low-resource languages from FLORES-200 with two LLMs: ChatGPT and BLOOMZ. Evaluation across three different metrics reveals that TALENT consistently enhances translation performance by 14.8% compared to zero-shot baselines. Further analysis demonstrates that TALENT not only improves LLMs’ comprehension of low-resource languages but also equips them with the knowledge needed to generate accurate and fluent sentences in these languages.
%U https://aclanthology.org/2024.lrec-main.1362
%P 15685-15697
Markdown (Informal)
[Teaching Large Language Models to Translate on Low-resource Languages with Textbook Prompting](https://aclanthology.org/2024.lrec-main.1362) (Guo et al., LREC-COLING 2024)
ACL
- Ping Guo, Yubing Ren, Yue Hu, Yunpeng Li, Jiarui Zhang, Xingsheng Zhang, and Heyan Huang. 2024. Teaching Large Language Models to Translate on Low-resource Languages with Textbook Prompting. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15685–15697, Torino, Italia. ELRA and ICCL.