@inproceedings{sawczyn-etal-2024-developing,
title = "Developing {PUGG} for {P}olish: A Modern Approach to {KBQA}, {MRC}, and {IR} Dataset Construction",
author = "Sawczyn, Albert and
Viarenich, Katsiaryna and
Wojtasik, Konrad and
Domoga{\l}a, Aleksandra and
Oleksy, Marcin and
Piasecki, Maciej and
Kajdanowicz, Tomasz",
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.652",
pages = "10978--10996",
abstract = "Advancements in AI and natural language processing have revolutionized machine-human language interactions, with question answering (QA) systems playing a pivotal role. The knowledge base question answering (KBQA) task, utilizing structured knowledge graphs (KG), allows for handling extensive knowledge-intensive questions. However, a significant gap exists in KBQA datasets, especially for low-resource languages. Many existing construction pipelines for these datasets are outdated and inefficient in human labor, and modern assisting tools like Large Language Models (LLM) are not utilized to reduce the workload. To address this, we have designed and implemented a modern, semi-automated approach for creating datasets, encompassing tasks such as KBQA, Machine Reading Comprehension (MRC), and Information Retrieval (IR), tailored explicitly for low-resource environments. We executed this pipeline and introduced the PUGG dataset, the first Polish KBQA dataset, and novel datasets for MRC and IR. Additionally, we provide a comprehensive implementation, insightful findings, detailed statistics, and evaluation of baseline models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sawczyn-etal-2024-developing">
<titleInfo>
<title>Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Sawczyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsiaryna</namePart>
<namePart type="family">Viarenich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konrad</namePart>
<namePart type="family">Wojtasik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandra</namePart>
<namePart type="family">Domogała</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcin</namePart>
<namePart type="family">Oleksy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Piasecki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Kajdanowicz</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>Advancements in AI and natural language processing have revolutionized machine-human language interactions, with question answering (QA) systems playing a pivotal role. The knowledge base question answering (KBQA) task, utilizing structured knowledge graphs (KG), allows for handling extensive knowledge-intensive questions. However, a significant gap exists in KBQA datasets, especially for low-resource languages. Many existing construction pipelines for these datasets are outdated and inefficient in human labor, and modern assisting tools like Large Language Models (LLM) are not utilized to reduce the workload. To address this, we have designed and implemented a modern, semi-automated approach for creating datasets, encompassing tasks such as KBQA, Machine Reading Comprehension (MRC), and Information Retrieval (IR), tailored explicitly for low-resource environments. We executed this pipeline and introduced the PUGG dataset, the first Polish KBQA dataset, and novel datasets for MRC and IR. Additionally, we provide a comprehensive implementation, insightful findings, detailed statistics, and evaluation of baseline models.</abstract>
<identifier type="citekey">sawczyn-etal-2024-developing</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.652</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>10978</start>
<end>10996</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction
%A Sawczyn, Albert
%A Viarenich, Katsiaryna
%A Wojtasik, Konrad
%A Domogała, Aleksandra
%A Oleksy, Marcin
%A Piasecki, Maciej
%A Kajdanowicz, Tomasz
%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 sawczyn-etal-2024-developing
%X Advancements in AI and natural language processing have revolutionized machine-human language interactions, with question answering (QA) systems playing a pivotal role. The knowledge base question answering (KBQA) task, utilizing structured knowledge graphs (KG), allows for handling extensive knowledge-intensive questions. However, a significant gap exists in KBQA datasets, especially for low-resource languages. Many existing construction pipelines for these datasets are outdated and inefficient in human labor, and modern assisting tools like Large Language Models (LLM) are not utilized to reduce the workload. To address this, we have designed and implemented a modern, semi-automated approach for creating datasets, encompassing tasks such as KBQA, Machine Reading Comprehension (MRC), and Information Retrieval (IR), tailored explicitly for low-resource environments. We executed this pipeline and introduced the PUGG dataset, the first Polish KBQA dataset, and novel datasets for MRC and IR. Additionally, we provide a comprehensive implementation, insightful findings, detailed statistics, and evaluation of baseline models.
%U https://aclanthology.org/2024.findings-acl.652
%P 10978-10996
Markdown (Informal)
[Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction](https://aclanthology.org/2024.findings-acl.652) (Sawczyn et al., Findings 2024)
ACL
- Albert Sawczyn, Katsiaryna Viarenich, Konrad Wojtasik, Aleksandra Domogała, Marcin Oleksy, Maciej Piasecki, and Tomasz Kajdanowicz. 2024. Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction. In Findings of the Association for Computational Linguistics ACL 2024, pages 10978–10996, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.