@inproceedings{lee-etal-2020-squad2,
title = "{SQ}u{AD}2-{CR}: Semi-supervised Annotation for Cause and Rationales for Unanswerability in {SQ}u{AD} 2.0",
author = "Lee, Gyeongbok and
Hwang, Seung-won and
Cho, Hyunsouk",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.667",
pages = "5425--5432",
abstract = "Existing machine reading comprehension models are reported to be brittle for adversarially perturbed questions when optimizing only for accuracy, which led to the creation of new reading comprehension benchmarks, such as SQuAD 2.0 which contains such type of questions. However, despite the super-human accuracy of existing models on such datasets, it is still unclear how the model predicts the answerability of the question, potentially due to the absence of a shared annotation for the explanation. To address such absence, we release SQuAD2-CR dataset, which contains annotations on unanswerable questions from the SQuAD 2.0 dataset, to enable an explanatory analysis of the model prediction. Specifically, we annotate (1) explanation on why the most plausible answer span cannot be the answer and (2) which part of the question causes unanswerability. We share intuitions and experimental results that how this dataset can be used to analyze and improve the interpretability of existing reading comprehension model behavior.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2020-squad2">
<titleInfo>
<title>SQuAD2-CR: Semi-supervised Annotation for Cause and Rationales for Unanswerability in SQuAD 2.0</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gyeongbok</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-won</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunsouk</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Existing machine reading comprehension models are reported to be brittle for adversarially perturbed questions when optimizing only for accuracy, which led to the creation of new reading comprehension benchmarks, such as SQuAD 2.0 which contains such type of questions. However, despite the super-human accuracy of existing models on such datasets, it is still unclear how the model predicts the answerability of the question, potentially due to the absence of a shared annotation for the explanation. To address such absence, we release SQuAD2-CR dataset, which contains annotations on unanswerable questions from the SQuAD 2.0 dataset, to enable an explanatory analysis of the model prediction. Specifically, we annotate (1) explanation on why the most plausible answer span cannot be the answer and (2) which part of the question causes unanswerability. We share intuitions and experimental results that how this dataset can be used to analyze and improve the interpretability of existing reading comprehension model behavior.</abstract>
<identifier type="citekey">lee-etal-2020-squad2</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.667</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5425</start>
<end>5432</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SQuAD2-CR: Semi-supervised Annotation for Cause and Rationales for Unanswerability in SQuAD 2.0
%A Lee, Gyeongbok
%A Hwang, Seung-won
%A Cho, Hyunsouk
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F lee-etal-2020-squad2
%X Existing machine reading comprehension models are reported to be brittle for adversarially perturbed questions when optimizing only for accuracy, which led to the creation of new reading comprehension benchmarks, such as SQuAD 2.0 which contains such type of questions. However, despite the super-human accuracy of existing models on such datasets, it is still unclear how the model predicts the answerability of the question, potentially due to the absence of a shared annotation for the explanation. To address such absence, we release SQuAD2-CR dataset, which contains annotations on unanswerable questions from the SQuAD 2.0 dataset, to enable an explanatory analysis of the model prediction. Specifically, we annotate (1) explanation on why the most plausible answer span cannot be the answer and (2) which part of the question causes unanswerability. We share intuitions and experimental results that how this dataset can be used to analyze and improve the interpretability of existing reading comprehension model behavior.
%U https://aclanthology.org/2020.lrec-1.667
%P 5425-5432
Markdown (Informal)
[SQuAD2-CR: Semi-supervised Annotation for Cause and Rationales for Unanswerability in SQuAD 2.0](https://aclanthology.org/2020.lrec-1.667) (Lee et al., LREC 2020)
ACL