@inproceedings{shah-etal-2020-expect,
title = "What do we expect from Multiple-choice {QA} Systems?",
author = "Shah, Krunal and
Gupta, Nitish and
Roth, Dan",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.317/",
doi = "10.18653/v1/2020.findings-emnlp.317",
pages = "3547--3553",
abstract = "The recent success of machine learning systems on various QA datasets could be interpreted as a significant improvement in models' language understanding abilities. However, using various perturbations, multiple recent works have shown that good performance on a dataset might not indicate performance that correlates well with human`s expectations from models that {\textquotedblleft}understand{\textquotedblright} language. In this work we consider a top performing model on several Multiple Choice Question Answering (MCQA) datasets, and evaluate it against a set of expectations one might have from such a model, using a series of zero-information perturbations of the model`s inputs. Our results show that the model clearly falls short of our expectations, and motivates a modified training approach that forces the model to better attend to the inputs. We show that the new training paradigm leads to a model that performs on par with the original model while better satisfying our expectations."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shah-etal-2020-expect">
<titleInfo>
<title>What do we expect from Multiple-choice QA Systems?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Krunal</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitish</namePart>
<namePart type="family">Gupta</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>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The recent success of machine learning systems on various QA datasets could be interpreted as a significant improvement in models’ language understanding abilities. However, using various perturbations, multiple recent works have shown that good performance on a dataset might not indicate performance that correlates well with human‘s expectations from models that “understand” language. In this work we consider a top performing model on several Multiple Choice Question Answering (MCQA) datasets, and evaluate it against a set of expectations one might have from such a model, using a series of zero-information perturbations of the model‘s inputs. Our results show that the model clearly falls short of our expectations, and motivates a modified training approach that forces the model to better attend to the inputs. We show that the new training paradigm leads to a model that performs on par with the original model while better satisfying our expectations.</abstract>
<identifier type="citekey">shah-etal-2020-expect</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.317</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.317/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3547</start>
<end>3553</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What do we expect from Multiple-choice QA Systems?
%A Shah, Krunal
%A Gupta, Nitish
%A Roth, Dan
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F shah-etal-2020-expect
%X The recent success of machine learning systems on various QA datasets could be interpreted as a significant improvement in models’ language understanding abilities. However, using various perturbations, multiple recent works have shown that good performance on a dataset might not indicate performance that correlates well with human‘s expectations from models that “understand” language. In this work we consider a top performing model on several Multiple Choice Question Answering (MCQA) datasets, and evaluate it against a set of expectations one might have from such a model, using a series of zero-information perturbations of the model‘s inputs. Our results show that the model clearly falls short of our expectations, and motivates a modified training approach that forces the model to better attend to the inputs. We show that the new training paradigm leads to a model that performs on par with the original model while better satisfying our expectations.
%R 10.18653/v1/2020.findings-emnlp.317
%U https://aclanthology.org/2020.findings-emnlp.317/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.317
%P 3547-3553
Markdown (Informal)
[What do we expect from Multiple-choice QA Systems?](https://aclanthology.org/2020.findings-emnlp.317/) (Shah et al., Findings 2020)
ACL