@inproceedings{pang-etal-2022-quality,
title = "{Q}u{ALITY}: Question Answering with Long Input Texts, Yes!",
author = "Pang, Richard Yuanzhe and
Parrish, Alicia and
Joshi, Nitish and
Nangia, Nikita and
Phang, Jason and
Chen, Angelica and
Padmakumar, Vishakh and
Ma, Johnny and
Thompson, Jana and
He, He and
Bowman, Samuel",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.391",
doi = "10.18653/v1/2022.naacl-main.391",
pages = "5336--5358",
abstract = "To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our questions are written and validated by contributors who have read the entire passage, rather than relying on summaries or excerpts. In addition, only half of the questions are answerable by annotators working under tight time constraints, indicating that skimming and simple search are not enough to consistently perform well. Our baseline models perform poorly on this task (55.4{\%}) and significantly lag behind human performance (93.5{\%}).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pang-etal-2022-quality">
<titleInfo>
<title>QuALITY: Question Answering with Long Input Texts, Yes!</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">Yuanzhe</namePart>
<namePart type="family">Pang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Parrish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitish</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Nangia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Phang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angelica</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishakh</namePart>
<namePart type="family">Padmakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johnny</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jana</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Bowman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our questions are written and validated by contributors who have read the entire passage, rather than relying on summaries or excerpts. In addition, only half of the questions are answerable by annotators working under tight time constraints, indicating that skimming and simple search are not enough to consistently perform well. Our baseline models perform poorly on this task (55.4%) and significantly lag behind human performance (93.5%).</abstract>
<identifier type="citekey">pang-etal-2022-quality</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.391</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.391</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>5336</start>
<end>5358</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QuALITY: Question Answering with Long Input Texts, Yes!
%A Pang, Richard Yuanzhe
%A Parrish, Alicia
%A Joshi, Nitish
%A Nangia, Nikita
%A Phang, Jason
%A Chen, Angelica
%A Padmakumar, Vishakh
%A Ma, Johnny
%A Thompson, Jana
%A He, He
%A Bowman, Samuel
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F pang-etal-2022-quality
%X To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our questions are written and validated by contributors who have read the entire passage, rather than relying on summaries or excerpts. In addition, only half of the questions are answerable by annotators working under tight time constraints, indicating that skimming and simple search are not enough to consistently perform well. Our baseline models perform poorly on this task (55.4%) and significantly lag behind human performance (93.5%).
%R 10.18653/v1/2022.naacl-main.391
%U https://aclanthology.org/2022.naacl-main.391
%U https://doi.org/10.18653/v1/2022.naacl-main.391
%P 5336-5358
Markdown (Informal)
[QuALITY: Question Answering with Long Input Texts, Yes!](https://aclanthology.org/2022.naacl-main.391) (Pang et al., NAACL 2022)
ACL
- Richard Yuanzhe Pang, Alicia Parrish, Nitish Joshi, Nikita Nangia, Jason Phang, Angelica Chen, Vishakh Padmakumar, Johnny Ma, Jana Thompson, He He, and Samuel Bowman. 2022. QuALITY: Question Answering with Long Input Texts, Yes!. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5336–5358, Seattle, United States. Association for Computational Linguistics.