@inproceedings{moller-etal-2021-germanquad,
title = "{G}erman{Q}u{AD} and {G}erman{DPR}: Improving Non-{E}nglish Question Answering and Passage Retrieval",
author = {M{\"o}ller, Timo and
Risch, Julian and
Pietsch, Malte},
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-1.4",
doi = "10.18653/v1/2021.mrqa-1.4",
pages = "42--50",
abstract = "A major challenge of research on non-English machine reading for question answering (QA) is the lack of annotated datasets. In this paper, we present GermanQuAD, a dataset of 13,722 extractive question/answer pairs. To improve the reproducibility of the dataset creation approach and foster QA research on other languages, we summarize lessons learned and evaluate reformulation of question/answer pairs as a way to speed up the annotation process. An extractive QA model trained on GermanQuAD significantly outperforms multilingual models and also shows that machine-translated training data cannot fully substitute hand-annotated training data in the target language. Finally, we demonstrate the wide range of applications of GermanQuAD by adapting it to GermanDPR, a training dataset for dense passage retrieval (DPR), and train and evaluate one of the first non-English DPR models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moller-etal-2021-germanquad">
<titleInfo>
<title>GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Timo</namePart>
<namePart type="family">Möller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Risch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malte</namePart>
<namePart type="family">Pietsch</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>A major challenge of research on non-English machine reading for question answering (QA) is the lack of annotated datasets. In this paper, we present GermanQuAD, a dataset of 13,722 extractive question/answer pairs. To improve the reproducibility of the dataset creation approach and foster QA research on other languages, we summarize lessons learned and evaluate reformulation of question/answer pairs as a way to speed up the annotation process. An extractive QA model trained on GermanQuAD significantly outperforms multilingual models and also shows that machine-translated training data cannot fully substitute hand-annotated training data in the target language. Finally, we demonstrate the wide range of applications of GermanQuAD by adapting it to GermanDPR, a training dataset for dense passage retrieval (DPR), and train and evaluate one of the first non-English DPR models.</abstract>
<identifier type="citekey">moller-etal-2021-germanquad</identifier>
<identifier type="doi">10.18653/v1/2021.mrqa-1.4</identifier>
<location>
<url>https://aclanthology.org/2021.mrqa-1.4</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>42</start>
<end>50</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval
%A Möller, Timo
%A Risch, Julian
%A Pietsch, Malte
%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 moller-etal-2021-germanquad
%X A major challenge of research on non-English machine reading for question answering (QA) is the lack of annotated datasets. In this paper, we present GermanQuAD, a dataset of 13,722 extractive question/answer pairs. To improve the reproducibility of the dataset creation approach and foster QA research on other languages, we summarize lessons learned and evaluate reformulation of question/answer pairs as a way to speed up the annotation process. An extractive QA model trained on GermanQuAD significantly outperforms multilingual models and also shows that machine-translated training data cannot fully substitute hand-annotated training data in the target language. Finally, we demonstrate the wide range of applications of GermanQuAD by adapting it to GermanDPR, a training dataset for dense passage retrieval (DPR), and train and evaluate one of the first non-English DPR models.
%R 10.18653/v1/2021.mrqa-1.4
%U https://aclanthology.org/2021.mrqa-1.4
%U https://doi.org/10.18653/v1/2021.mrqa-1.4
%P 42-50
Markdown (Informal)
[GermanQuAD and GermanDPR: Improving Non-English Question Answering and Passage Retrieval](https://aclanthology.org/2021.mrqa-1.4) (Möller et al., MRQA 2021)
ACL