@inproceedings{dzendzik-etal-2021-english,
title = "{E}nglish Machine Reading Comprehension Datasets: A Survey",
author = "Dzendzik, Daria and
Foster, Jennifer and
Vogel, Carl",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.693",
doi = "10.18653/v1/2021.emnlp-main.693",
pages = "8784--8804",
abstract = "This paper surveys 60 English Machine Reading Comprehension datasets, with a view to providing a convenient resource for other researchers interested in this problem. We categorize the datasets according to their question and answer form and compare them across various dimensions including size, vocabulary, data source, method of creation, human performance level, and first question word. Our analysis reveals that Wikipedia is by far the most common data source and that there is a relative lack of why, when, and where questions across datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dzendzik-etal-2021-english">
<titleInfo>
<title>English Machine Reading Comprehension Datasets: A Survey</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daria</namePart>
<namePart type="family">Dzendzik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carl</namePart>
<namePart type="family">Vogel</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 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper surveys 60 English Machine Reading Comprehension datasets, with a view to providing a convenient resource for other researchers interested in this problem. We categorize the datasets according to their question and answer form and compare them across various dimensions including size, vocabulary, data source, method of creation, human performance level, and first question word. Our analysis reveals that Wikipedia is by far the most common data source and that there is a relative lack of why, when, and where questions across datasets.</abstract>
<identifier type="citekey">dzendzik-etal-2021-english</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.693</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.693</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>8784</start>
<end>8804</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T English Machine Reading Comprehension Datasets: A Survey
%A Dzendzik, Daria
%A Foster, Jennifer
%A Vogel, Carl
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F dzendzik-etal-2021-english
%X This paper surveys 60 English Machine Reading Comprehension datasets, with a view to providing a convenient resource for other researchers interested in this problem. We categorize the datasets according to their question and answer form and compare them across various dimensions including size, vocabulary, data source, method of creation, human performance level, and first question word. Our analysis reveals that Wikipedia is by far the most common data source and that there is a relative lack of why, when, and where questions across datasets.
%R 10.18653/v1/2021.emnlp-main.693
%U https://aclanthology.org/2021.emnlp-main.693
%U https://doi.org/10.18653/v1/2021.emnlp-main.693
%P 8784-8804
Markdown (Informal)
[English Machine Reading Comprehension Datasets: A Survey](https://aclanthology.org/2021.emnlp-main.693) (Dzendzik et al., EMNLP 2021)
ACL
- Daria Dzendzik, Jennifer Foster, and Carl Vogel. 2021. English Machine Reading Comprehension Datasets: A Survey. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8784–8804, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.