ZeLa: Advancing Zero-Shot Multilingual Semantic Parsing with Large Language Models and Chain-of-Thought Strategies

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AW6M42CKW" target="_blank" >RIV/00216208:11320/25:W6M42CKW - isvavai.cz</a>

Result on the web

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195893284&partnerID=40&md5=d699e38af5aa430cd4b8b022a4c01388" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195893284&partnerID=40&md5=d699e38af5aa430cd4b8b022a4c01388</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

ZeLa: Advancing Zero-Shot Multilingual Semantic Parsing with Large Language Models and Chain-of-Thought Strategies

Original language description

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. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Jt. Int. Conf. Comput. Linguist., Lang. Resour. Eval., LREC-COLING - Main Conf. Proc.

ISBN

978-249381410-4

ISSN

—

e-ISSN

—

Number of pages

12

Pages from-to

17783-17794

Publisher name

European Language Resources Association (ELRA)

Place of publication

—

Event location

Torino, Italia

Event date

Jan 1, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—