@inproceedings{sulem-etal-2021-know-dont,
title = "Do We Know What We Don{'}t Know? Studying Unanswerable Questions beyond {SQ}u{AD} 2.0",
author = "Sulem, Elior and
Hay, Jamaal and
Roth, Dan",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.385",
doi = "10.18653/v1/2021.findings-emnlp.385",
pages = "4543--4548",
abstract = "Understanding when a text snippet does not provide a sought after information is an essential part of natural language utnderstanding. Recent work (SQuAD 2.0; Rajpurkar et al., 2018) has attempted to make some progress in this direction by enriching the SQuAD dataset for the Extractive QA task with unanswerable questions. However, as we show, the performance of a top system trained on SQuAD 2.0 drops considerably in out-of-domain scenarios, limiting its use in practical situations. In order to study this we build an out-of-domain corpus, focusing on simple event-based questions and distinguish between two types of IDK questions: competitive questions, where the context includes an entity of the same type as the expected answer, and simpler, non-competitive questions where there is no entity of the same type in the context. We find that SQuAD 2.0-based models fail even in the case of the simpler questions. We then analyze the similarities and differences between the IDK phenomenon in Extractive QA and the Recognizing Textual Entailments task (RTE; Dagan et al., 2013) and investigate the extent to which the latter can be used to improve the performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sulem-etal-2021-know-dont">
<titleInfo>
<title>Do We Know What We Don’t Know? Studying Unanswerable Questions beyond SQuAD 2.0</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elior</namePart>
<namePart type="family">Sulem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamaal</namePart>
<namePart type="family">Hay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Roth</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>Findings of the Association for Computational Linguistics: EMNLP 2021</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">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Understanding when a text snippet does not provide a sought after information is an essential part of natural language utnderstanding. Recent work (SQuAD 2.0; Rajpurkar et al., 2018) has attempted to make some progress in this direction by enriching the SQuAD dataset for the Extractive QA task with unanswerable questions. However, as we show, the performance of a top system trained on SQuAD 2.0 drops considerably in out-of-domain scenarios, limiting its use in practical situations. In order to study this we build an out-of-domain corpus, focusing on simple event-based questions and distinguish between two types of IDK questions: competitive questions, where the context includes an entity of the same type as the expected answer, and simpler, non-competitive questions where there is no entity of the same type in the context. We find that SQuAD 2.0-based models fail even in the case of the simpler questions. We then analyze the similarities and differences between the IDK phenomenon in Extractive QA and the Recognizing Textual Entailments task (RTE; Dagan et al., 2013) and investigate the extent to which the latter can be used to improve the performance.</abstract>
<identifier type="citekey">sulem-etal-2021-know-dont</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.385</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.385</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4543</start>
<end>4548</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do We Know What We Don’t Know? Studying Unanswerable Questions beyond SQuAD 2.0
%A Sulem, Elior
%A Hay, Jamaal
%A Roth, Dan
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F sulem-etal-2021-know-dont
%X Understanding when a text snippet does not provide a sought after information is an essential part of natural language utnderstanding. Recent work (SQuAD 2.0; Rajpurkar et al., 2018) has attempted to make some progress in this direction by enriching the SQuAD dataset for the Extractive QA task with unanswerable questions. However, as we show, the performance of a top system trained on SQuAD 2.0 drops considerably in out-of-domain scenarios, limiting its use in practical situations. In order to study this we build an out-of-domain corpus, focusing on simple event-based questions and distinguish between two types of IDK questions: competitive questions, where the context includes an entity of the same type as the expected answer, and simpler, non-competitive questions where there is no entity of the same type in the context. We find that SQuAD 2.0-based models fail even in the case of the simpler questions. We then analyze the similarities and differences between the IDK phenomenon in Extractive QA and the Recognizing Textual Entailments task (RTE; Dagan et al., 2013) and investigate the extent to which the latter can be used to improve the performance.
%R 10.18653/v1/2021.findings-emnlp.385
%U https://aclanthology.org/2021.findings-emnlp.385
%U https://doi.org/10.18653/v1/2021.findings-emnlp.385
%P 4543-4548
Markdown (Informal)
[Do We Know What We Don’t Know? Studying Unanswerable Questions beyond SQuAD 2.0](https://aclanthology.org/2021.findings-emnlp.385) (Sulem et al., Findings 2021)
ACL