@inproceedings{rybak-2023-maupqa,
title = "{MAUPQA}: Massive Automatically-created {P}olish Question Answering Dataset",
author = "Rybak, Piotr",
editor = "Piskorski, Jakub and
Marci{\'n}czuk, Micha{\l} and
Nakov, Preslav and
Ogrodniczuk, Maciej and
Pollak, Senja and
P{\v{r}}ib{\'a}{\v{n}}, Pavel and
Rybak, Piotr and
Steinberger, Josef and
Yangarber, Roman",
booktitle = "Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bsnlp-1.2",
doi = "10.18653/v1/2023.bsnlp-1.2",
pages = "11--16",
abstract = "Recently, open-domain question answering systems have begun to rely heavily on annotated datasets to train neural passage retrievers. However, manually annotating such datasets is both difficult and time-consuming, which limits their availability for less popular languages. In this work, we experiment with several methods for automatically collecting weakly labeled datasets and show how they affect the performance of the neural passage retrieval models. As a result of our work, we publish the MAUPQA dataset, consisting of nearly 400,000 question-passage pairs for Polish, as well as the HerBERT-QA neural retriever.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rybak-2023-maupqa">
<titleInfo>
<title>MAUPQA: Massive Automatically-created Polish Question Answering Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Rybak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Marcińczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Senja</namePart>
<namePart type="family">Pollak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Přibáň</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Rybak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, open-domain question answering systems have begun to rely heavily on annotated datasets to train neural passage retrievers. However, manually annotating such datasets is both difficult and time-consuming, which limits their availability for less popular languages. In this work, we experiment with several methods for automatically collecting weakly labeled datasets and show how they affect the performance of the neural passage retrieval models. As a result of our work, we publish the MAUPQA dataset, consisting of nearly 400,000 question-passage pairs for Polish, as well as the HerBERT-QA neural retriever.</abstract>
<identifier type="citekey">rybak-2023-maupqa</identifier>
<identifier type="doi">10.18653/v1/2023.bsnlp-1.2</identifier>
<location>
<url>https://aclanthology.org/2023.bsnlp-1.2</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>11</start>
<end>16</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAUPQA: Massive Automatically-created Polish Question Answering Dataset
%A Rybak, Piotr
%Y Piskorski, Jakub
%Y Marcińczuk, Michał
%Y Nakov, Preslav
%Y Ogrodniczuk, Maciej
%Y Pollak, Senja
%Y Přibáň, Pavel
%Y Rybak, Piotr
%Y Steinberger, Josef
%Y Yangarber, Roman
%S Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F rybak-2023-maupqa
%X Recently, open-domain question answering systems have begun to rely heavily on annotated datasets to train neural passage retrievers. However, manually annotating such datasets is both difficult and time-consuming, which limits their availability for less popular languages. In this work, we experiment with several methods for automatically collecting weakly labeled datasets and show how they affect the performance of the neural passage retrieval models. As a result of our work, we publish the MAUPQA dataset, consisting of nearly 400,000 question-passage pairs for Polish, as well as the HerBERT-QA neural retriever.
%R 10.18653/v1/2023.bsnlp-1.2
%U https://aclanthology.org/2023.bsnlp-1.2
%U https://doi.org/10.18653/v1/2023.bsnlp-1.2
%P 11-16
Markdown (Informal)
[MAUPQA: Massive Automatically-created Polish Question Answering Dataset](https://aclanthology.org/2023.bsnlp-1.2) (Rybak, BSNLP 2023)
ACL