@inproceedings{martinez-lorenzo-etal-2024-mitigating,
title = "Mitigating Data Scarcity in Semantic Parsing across Languages with the Multilingual Semantic Layer and its Dataset",
author = "Martinez Lorenzo, Abelardo Carlos and
Huguet Cabot, Pere-Llu{\'\i}s and
Ghonim, Karim and
Xu, Lu and
Choi, Hee-Soo and
Fern{\'a}ndez-Castro, Alberte and
Navigli, Roberto",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.836",
pages = "14056--14080",
abstract = "Data scarcity is a prevalent challenge in the era of Large Language Models (LLMs). The insatiable hunger of LLMs for large corpora becomes even more pronounced when dealing with non-English and low-resource languages. The issue is particularly exacerbated in Semantic Parsing (SP), i.e. the task of converting text into a formal representation. The complexity of semantic formalisms makes training human annotators and subsequent data annotation unfeasible on a large scale, especially across languages. To mitigate this, we first introduce the Multilingual Semantic Layer (MSL), a conceptual evolution of previous formalisms, which decouples from disambiguation and external inventories and simplifies the task. MSL provides the necessary tools to encode the meaning across languages, paving the way for developing a high-quality semantic parsing dataset across different languages in a semi-automatic strategy. Subsequently, we manually refine a portion of this dataset and fine-tune GPT-3.5 to propagate these refinements across the dataset. Then, we manually annotate 1,100 sentences in eleven languages, including low-resource ones. Finally, we assess our dataset{'}s quality, showcasing the performance gap reduction across languages in Semantic Parsing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martinez-lorenzo-etal-2024-mitigating">
<titleInfo>
<title>Mitigating Data Scarcity in Semantic Parsing across Languages with the Multilingual Semantic Layer and its Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abelardo</namePart>
<namePart type="given">Carlos</namePart>
<namePart type="family">Martinez Lorenzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pere-Lluís</namePart>
<namePart type="family">Huguet Cabot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karim</namePart>
<namePart type="family">Ghonim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hee-Soo</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberte</namePart>
<namePart type="family">Fernández-Castro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data scarcity is a prevalent challenge in the era of Large Language Models (LLMs). The insatiable hunger of LLMs for large corpora becomes even more pronounced when dealing with non-English and low-resource languages. The issue is particularly exacerbated in Semantic Parsing (SP), i.e. the task of converting text into a formal representation. The complexity of semantic formalisms makes training human annotators and subsequent data annotation unfeasible on a large scale, especially across languages. To mitigate this, we first introduce the Multilingual Semantic Layer (MSL), a conceptual evolution of previous formalisms, which decouples from disambiguation and external inventories and simplifies the task. MSL provides the necessary tools to encode the meaning across languages, paving the way for developing a high-quality semantic parsing dataset across different languages in a semi-automatic strategy. Subsequently, we manually refine a portion of this dataset and fine-tune GPT-3.5 to propagate these refinements across the dataset. Then, we manually annotate 1,100 sentences in eleven languages, including low-resource ones. Finally, we assess our dataset’s quality, showcasing the performance gap reduction across languages in Semantic Parsing.</abstract>
<identifier type="citekey">martinez-lorenzo-etal-2024-mitigating</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.836</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14056</start>
<end>14080</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mitigating Data Scarcity in Semantic Parsing across Languages with the Multilingual Semantic Layer and its Dataset
%A Martinez Lorenzo, Abelardo Carlos
%A Huguet Cabot, Pere-Lluís
%A Ghonim, Karim
%A Xu, Lu
%A Choi, Hee-Soo
%A Fernández-Castro, Alberte
%A Navigli, Roberto
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F martinez-lorenzo-etal-2024-mitigating
%X Data scarcity is a prevalent challenge in the era of Large Language Models (LLMs). The insatiable hunger of LLMs for large corpora becomes even more pronounced when dealing with non-English and low-resource languages. The issue is particularly exacerbated in Semantic Parsing (SP), i.e. the task of converting text into a formal representation. The complexity of semantic formalisms makes training human annotators and subsequent data annotation unfeasible on a large scale, especially across languages. To mitigate this, we first introduce the Multilingual Semantic Layer (MSL), a conceptual evolution of previous formalisms, which decouples from disambiguation and external inventories and simplifies the task. MSL provides the necessary tools to encode the meaning across languages, paving the way for developing a high-quality semantic parsing dataset across different languages in a semi-automatic strategy. Subsequently, we manually refine a portion of this dataset and fine-tune GPT-3.5 to propagate these refinements across the dataset. Then, we manually annotate 1,100 sentences in eleven languages, including low-resource ones. Finally, we assess our dataset’s quality, showcasing the performance gap reduction across languages in Semantic Parsing.
%U https://aclanthology.org/2024.findings-acl.836
%P 14056-14080
Markdown (Informal)
[Mitigating Data Scarcity in Semantic Parsing across Languages with the Multilingual Semantic Layer and its Dataset](https://aclanthology.org/2024.findings-acl.836) (Martinez Lorenzo et al., Findings 2024)
ACL