@inproceedings{keren-levy-2021-parashoot,
title = "{P}ara{S}hoot: A {H}ebrew Question Answering Dataset",
author = "Keren, Omri and
Levy, Omer",
editor = "Fisch, Adam and
Talmor, Alon and
Chen, Danqi and
Choi, Eunsol and
Seo, Minjoon and
Lewis, Patrick and
Jia, Robin and
Min, Sewon",
booktitle = "Proceedings of the 3rd Workshop on Machine Reading for Question Answering",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.mrqa-1.11",
doi = "10.18653/v1/2021.mrqa-1.11",
pages = "106--112",
abstract = "NLP research in Hebrew has largely focused on morphology and syntax, where rich annotated datasets in the spirit of Universal Dependencies are available. Semantic datasets, however, are in short supply, hindering crucial advances in the development of NLP technology in Hebrew. In this work, we present ParaShoot, the first question answering dataset in modern Hebrew. The dataset follows the format and crowdsourcing methodology of SQuAD, and contains approximately 3000 annotated examples, similar to other question-answering datasets in low-resource languages. We provide the first baseline results using recently-released BERT-style models for Hebrew, showing that there is significant room for improvement on this task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="keren-levy-2021-parashoot">
<titleInfo>
<title>ParaShoot: A Hebrew Question Answering Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Omri</namePart>
<namePart type="family">Keren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Levy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Machine Reading for Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Fisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Talmor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjoon</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sewon</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>NLP research in Hebrew has largely focused on morphology and syntax, where rich annotated datasets in the spirit of Universal Dependencies are available. Semantic datasets, however, are in short supply, hindering crucial advances in the development of NLP technology in Hebrew. In this work, we present ParaShoot, the first question answering dataset in modern Hebrew. The dataset follows the format and crowdsourcing methodology of SQuAD, and contains approximately 3000 annotated examples, similar to other question-answering datasets in low-resource languages. We provide the first baseline results using recently-released BERT-style models for Hebrew, showing that there is significant room for improvement on this task.</abstract>
<identifier type="citekey">keren-levy-2021-parashoot</identifier>
<identifier type="doi">10.18653/v1/2021.mrqa-1.11</identifier>
<location>
<url>https://aclanthology.org/2021.mrqa-1.11</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>106</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ParaShoot: A Hebrew Question Answering Dataset
%A Keren, Omri
%A Levy, Omer
%Y Fisch, Adam
%Y Talmor, Alon
%Y Chen, Danqi
%Y Choi, Eunsol
%Y Seo, Minjoon
%Y Lewis, Patrick
%Y Jia, Robin
%Y Min, Sewon
%S Proceedings of the 3rd Workshop on Machine Reading for Question Answering
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F keren-levy-2021-parashoot
%X NLP research in Hebrew has largely focused on morphology and syntax, where rich annotated datasets in the spirit of Universal Dependencies are available. Semantic datasets, however, are in short supply, hindering crucial advances in the development of NLP technology in Hebrew. In this work, we present ParaShoot, the first question answering dataset in modern Hebrew. The dataset follows the format and crowdsourcing methodology of SQuAD, and contains approximately 3000 annotated examples, similar to other question-answering datasets in low-resource languages. We provide the first baseline results using recently-released BERT-style models for Hebrew, showing that there is significant room for improvement on this task.
%R 10.18653/v1/2021.mrqa-1.11
%U https://aclanthology.org/2021.mrqa-1.11
%U https://doi.org/10.18653/v1/2021.mrqa-1.11
%P 106-112
Markdown (Informal)
[ParaShoot: A Hebrew Question Answering Dataset](https://aclanthology.org/2021.mrqa-1.11) (Keren & Levy, MRQA 2021)
ACL
- Omri Keren and Omer Levy. 2021. ParaShoot: A Hebrew Question Answering Dataset. In Proceedings of the 3rd Workshop on Machine Reading for Question Answering, pages 106–112, Punta Cana, Dominican Republic. Association for Computational Linguistics.