@inproceedings{trischler-etal-2017-newsqa,
title = "{N}ews{QA}: A Machine Comprehension Dataset",
author = "Trischler, Adam and
Wang, Tong and
Yuan, Xingdi and
Harris, Justin and
Sordoni, Alessandro and
Bachman, Philip and
Suleman, Kaheer",
editor = "Blunsom, Phil and
Bordes, Antoine and
Cho, Kyunghyun and
Cohen, Shay and
Dyer, Chris and
Grefenstette, Edward and
Hermann, Karl Moritz and
Rimell, Laura and
Weston, Jason and
Yih, Scott",
booktitle = "Proceedings of the 2nd Workshop on Representation Learning for {NLP}",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2623",
doi = "10.18653/v1/W17-2623",
pages = "191--200",
abstract = "We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans of text in the articles. We collect this dataset through a four-stage process designed to solicit exploratory questions that require reasoning. Analysis confirms that NewsQA demands abilities beyond simple word matching and recognizing textual entailment. We measure human performance on the dataset and compare it to several strong neural models. The performance gap between humans and machines (13.3{\%} F1) indicates that significant progress can be made on NewsQA through future research. The dataset is freely available online.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trischler-etal-2017-newsqa">
<titleInfo>
<title>NewsQA: A Machine Comprehension Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Trischler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingdi</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Harris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Sordoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Bachman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaheer</namePart>
<namePart type="family">Suleman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bordes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Dyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Grefenstette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karl</namePart>
<namePart type="given">Moritz</namePart>
<namePart type="family">Hermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Rimell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Weston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</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">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans of text in the articles. We collect this dataset through a four-stage process designed to solicit exploratory questions that require reasoning. Analysis confirms that NewsQA demands abilities beyond simple word matching and recognizing textual entailment. We measure human performance on the dataset and compare it to several strong neural models. The performance gap between humans and machines (13.3% F1) indicates that significant progress can be made on NewsQA through future research. The dataset is freely available online.</abstract>
<identifier type="citekey">trischler-etal-2017-newsqa</identifier>
<identifier type="doi">10.18653/v1/W17-2623</identifier>
<location>
<url>https://aclanthology.org/W17-2623</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>191</start>
<end>200</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NewsQA: A Machine Comprehension Dataset
%A Trischler, Adam
%A Wang, Tong
%A Yuan, Xingdi
%A Harris, Justin
%A Sordoni, Alessandro
%A Bachman, Philip
%A Suleman, Kaheer
%Y Blunsom, Phil
%Y Bordes, Antoine
%Y Cho, Kyunghyun
%Y Cohen, Shay
%Y Dyer, Chris
%Y Grefenstette, Edward
%Y Hermann, Karl Moritz
%Y Rimell, Laura
%Y Weston, Jason
%Y Yih, Scott
%S Proceedings of the 2nd Workshop on Representation Learning for NLP
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F trischler-etal-2017-newsqa
%X We present NewsQA, a challenging machine comprehension dataset of over 100,000 human-generated question-answer pairs. Crowdworkers supply questions and answers based on a set of over 10,000 news articles from CNN, with answers consisting of spans of text in the articles. We collect this dataset through a four-stage process designed to solicit exploratory questions that require reasoning. Analysis confirms that NewsQA demands abilities beyond simple word matching and recognizing textual entailment. We measure human performance on the dataset and compare it to several strong neural models. The performance gap between humans and machines (13.3% F1) indicates that significant progress can be made on NewsQA through future research. The dataset is freely available online.
%R 10.18653/v1/W17-2623
%U https://aclanthology.org/W17-2623
%U https://doi.org/10.18653/v1/W17-2623
%P 191-200
Markdown (Informal)
[NewsQA: A Machine Comprehension Dataset](https://aclanthology.org/W17-2623) (Trischler et al., RepL4NLP 2017)
ACL
- Adam Trischler, Tong Wang, Xingdi Yuan, Justin Harris, Alessandro Sordoni, Philip Bachman, and Kaheer Suleman. 2017. NewsQA: A Machine Comprehension Dataset. In Proceedings of the 2nd Workshop on Representation Learning for NLP, pages 191–200, Vancouver, Canada. Association for Computational Linguistics.