@inproceedings{do-etal-2024-zela-advancing,
title = "{Z}e{L}a: Advancing Zero-Shot Multilingual Semantic Parsing with Large Language Models and Chain-of-Thought Strategies",
author = "Do, Truong Dinh and
Nguyen, Phuong Minh and
Nguyen, Minh",
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.1547",
pages = "17783--17794",
abstract = "In recent years, there have been significant advancements in semantic parsing tasks, thanks to the introduction of pre-trained language models. However, a substantial gap persists between English and other languages due to the scarcity of annotated data. One promising strategy to bridge this gap involves augmenting multilingual datasets using labeled English data and subsequently leveraging this augmented dataset for training semantic parsers (known as zero-shot multilingual semantic parsing). In our study, we propose a novel framework to effectively perform zero-shot multilingual semantic parsing under the support of large language models (LLMs). Given data annotated pairs (sentence, semantic representation) in English, our proposed framework automatically augments data in other languages via multilingual chain-of-thought (CoT) prompting techniques that progressively construct the semantic form in these languages. By breaking down the entire semantic representation into sub-semantic fragments, our CoT prompting technique simplifies the intricate semantic structure at each step, thereby facilitating the LLMs in generating accurate outputs more efficiently. Notably, this entire augmentation process is achieved without the need for any demonstration samples in the target languages (zero-shot learning). In our experiments, we demonstrate the effectiveness of our method by evaluating it on two well-known multilingual semantic parsing datasets: MTOP and MASSIVE.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="do-etal-2024-zela-advancing">
<titleInfo>
<title>ZeLa: Advancing Zero-Shot Multilingual Semantic Parsing with Large Language Models and Chain-of-Thought Strategies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Truong</namePart>
<namePart type="given">Dinh</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phuong</namePart>
<namePart type="given">Minh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="family">Nguyen</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>In recent years, there have been significant advancements in semantic parsing tasks, thanks to the introduction of pre-trained language models. However, a substantial gap persists between English and other languages due to the scarcity of annotated data. One promising strategy to bridge this gap involves augmenting multilingual datasets using labeled English data and subsequently leveraging this augmented dataset for training semantic parsers (known as zero-shot multilingual semantic parsing). In our study, we propose a novel framework to effectively perform zero-shot multilingual semantic parsing under the support of large language models (LLMs). Given data annotated pairs (sentence, semantic representation) in English, our proposed framework automatically augments data in other languages via multilingual chain-of-thought (CoT) prompting techniques that progressively construct the semantic form in these languages. By breaking down the entire semantic representation into sub-semantic fragments, our CoT prompting technique simplifies the intricate semantic structure at each step, thereby facilitating the LLMs in generating accurate outputs more efficiently. Notably, this entire augmentation process is achieved without the need for any demonstration samples in the target languages (zero-shot learning). In our experiments, we demonstrate the effectiveness of our method by evaluating it on two well-known multilingual semantic parsing datasets: MTOP and MASSIVE.</abstract>
<identifier type="citekey">do-etal-2024-zela-advancing</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1547</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>17783</start>
<end>17794</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ZeLa: Advancing Zero-Shot Multilingual Semantic Parsing with Large Language Models and Chain-of-Thought Strategies
%A Do, Truong Dinh
%A Nguyen, Phuong Minh
%A Nguyen, Minh
%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 do-etal-2024-zela-advancing
%X In recent years, there have been significant advancements in semantic parsing tasks, thanks to the introduction of pre-trained language models. However, a substantial gap persists between English and other languages due to the scarcity of annotated data. One promising strategy to bridge this gap involves augmenting multilingual datasets using labeled English data and subsequently leveraging this augmented dataset for training semantic parsers (known as zero-shot multilingual semantic parsing). In our study, we propose a novel framework to effectively perform zero-shot multilingual semantic parsing under the support of large language models (LLMs). Given data annotated pairs (sentence, semantic representation) in English, our proposed framework automatically augments data in other languages via multilingual chain-of-thought (CoT) prompting techniques that progressively construct the semantic form in these languages. By breaking down the entire semantic representation into sub-semantic fragments, our CoT prompting technique simplifies the intricate semantic structure at each step, thereby facilitating the LLMs in generating accurate outputs more efficiently. Notably, this entire augmentation process is achieved without the need for any demonstration samples in the target languages (zero-shot learning). In our experiments, we demonstrate the effectiveness of our method by evaluating it on two well-known multilingual semantic parsing datasets: MTOP and MASSIVE.
%U https://aclanthology.org/2024.lrec-main.1547
%P 17783-17794
Markdown (Informal)
[ZeLa: Advancing Zero-Shot Multilingual Semantic Parsing with Large Language Models and Chain-of-Thought Strategies](https://aclanthology.org/2024.lrec-main.1547) (Do et al., LREC-COLING 2024)
ACL