@inproceedings{novak-etal-2023-question,
title = "A Question Answering Benchmark Database for {H}ungarian",
author = "Nov{\'a}k, Attila and
Nov{\'a}k, Borb{\'a}la and
Zombori, Tam{\'a}s and
Szab{\'o}, Gerg{\H{o}} and
Sz{\'a}nt{\'o}, Zsolt and
Farkas, Rich{\'a}rd",
editor = "Prange, Jakob and
Friedrich, Annemarie",
booktitle = "Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.law-1.19",
doi = "10.18653/v1/2023.law-1.19",
pages = "188--198",
abstract = "Within the research presented in this article, we created a new question answering benchmark database for Hungarian called MILQA. When creating the dataset, we basically followed the principles of the English SQuAD 2.0, however, like in some more recent English question answering datasets, we introduced a number of innovations beyond SQuAD: e.g., yes/no-questions, list-like answers consisting of several text spans, long answers, questions requiring calculation and other question types where you cannot simply copy the answer from the text. For all these non-extractive question types, the pragmatically adequate form of the answer was also added to make the training of generative models possible. We implemented and evaluated a set of baseline retrieval and answer span extraction models on the dataset. BM25 performed better than any vector-based solution for retrieval. Cross-lingual transfer from English significantly improved span extraction models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="novak-etal-2023-question">
<titleInfo>
<title>A Question Answering Benchmark Database for Hungarian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Attila</namePart>
<namePart type="family">Novák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Borbála</namePart>
<namePart type="family">Novák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamás</namePart>
<namePart type="family">Zombori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gergő</namePart>
<namePart type="family">Szabó</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zsolt</namePart>
<namePart type="family">Szántó</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richárd</namePart>
<namePart type="family">Farkas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Prange</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Within the research presented in this article, we created a new question answering benchmark database for Hungarian called MILQA. When creating the dataset, we basically followed the principles of the English SQuAD 2.0, however, like in some more recent English question answering datasets, we introduced a number of innovations beyond SQuAD: e.g., yes/no-questions, list-like answers consisting of several text spans, long answers, questions requiring calculation and other question types where you cannot simply copy the answer from the text. For all these non-extractive question types, the pragmatically adequate form of the answer was also added to make the training of generative models possible. We implemented and evaluated a set of baseline retrieval and answer span extraction models on the dataset. BM25 performed better than any vector-based solution for retrieval. Cross-lingual transfer from English significantly improved span extraction models.</abstract>
<identifier type="citekey">novak-etal-2023-question</identifier>
<identifier type="doi">10.18653/v1/2023.law-1.19</identifier>
<location>
<url>https://aclanthology.org/2023.law-1.19</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>188</start>
<end>198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Question Answering Benchmark Database for Hungarian
%A Novák, Attila
%A Novák, Borbála
%A Zombori, Tamás
%A Szabó, Gergő
%A Szántó, Zsolt
%A Farkas, Richárd
%Y Prange, Jakob
%Y Friedrich, Annemarie
%S Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F novak-etal-2023-question
%X Within the research presented in this article, we created a new question answering benchmark database for Hungarian called MILQA. When creating the dataset, we basically followed the principles of the English SQuAD 2.0, however, like in some more recent English question answering datasets, we introduced a number of innovations beyond SQuAD: e.g., yes/no-questions, list-like answers consisting of several text spans, long answers, questions requiring calculation and other question types where you cannot simply copy the answer from the text. For all these non-extractive question types, the pragmatically adequate form of the answer was also added to make the training of generative models possible. We implemented and evaluated a set of baseline retrieval and answer span extraction models on the dataset. BM25 performed better than any vector-based solution for retrieval. Cross-lingual transfer from English significantly improved span extraction models.
%R 10.18653/v1/2023.law-1.19
%U https://aclanthology.org/2023.law-1.19
%U https://doi.org/10.18653/v1/2023.law-1.19
%P 188-198
Markdown (Informal)
[A Question Answering Benchmark Database for Hungarian](https://aclanthology.org/2023.law-1.19) (Novák et al., LAW 2023)
ACL
- Attila Novák, Borbála Novák, Tamás Zombori, Gergő Szabó, Zsolt Szántó, and Richárd Farkas. 2023. A Question Answering Benchmark Database for Hungarian. In Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII), pages 188–198, Toronto, Canada. Association for Computational Linguistics.