@inproceedings{li-etal-2020-mrc,
title = "{MRC} Examples Answerable by {BERT} without a Question Are Less Effective in {MRC} Model Training",
author = "Li, Hongyu and
Chen, Tengyang and
Bai, Shuting and
Utsuro, Takehito and
Kawada, Yasuhide",
editor = "Shmueli, Boaz and
Huang, Yin Jou",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-srw.21",
pages = "146--152",
abstract = "Models developed for Machine Reading Comprehension (MRC) are asked to predict an answer from a question and its related context. However, there exist cases that can be correctly answered by an MRC model using BERT, where only the context is provided without including the question. In this paper, these types of examples are referred to as {``}easy to answer{''}, while others are as {``}hard to answer{''}, i.e., unanswerable by an MRC model using BERT without being provided the question. Based on classifying examples as answerable or unanswerable by BERT without the given question, we propose a method based on BERT that splits the training examples from the MRC dataset SQuAD1.1 into those that are {``}easy to answer{''} or {``}hard to answer{''}. Experimental evaluation from a comparison of two models, one trained only with {``}easy to answer{''} examples and the other with {``}hard to answer{''} examples demonstrates that the latter outperforms the former.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-mrc">
<titleInfo>
<title>MRC Examples Answerable by BERT without a Question Are Less Effective in MRC Model Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tengyang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuting</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takehito</namePart>
<namePart type="family">Utsuro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuhide</namePart>
<namePart type="family">Kawada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Boaz</namePart>
<namePart type="family">Shmueli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yin</namePart>
<namePart type="given">Jou</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Models developed for Machine Reading Comprehension (MRC) are asked to predict an answer from a question and its related context. However, there exist cases that can be correctly answered by an MRC model using BERT, where only the context is provided without including the question. In this paper, these types of examples are referred to as “easy to answer”, while others are as “hard to answer”, i.e., unanswerable by an MRC model using BERT without being provided the question. Based on classifying examples as answerable or unanswerable by BERT without the given question, we propose a method based on BERT that splits the training examples from the MRC dataset SQuAD1.1 into those that are “easy to answer” or “hard to answer”. Experimental evaluation from a comparison of two models, one trained only with “easy to answer” examples and the other with “hard to answer” examples demonstrates that the latter outperforms the former.</abstract>
<identifier type="citekey">li-etal-2020-mrc</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-srw.21</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>146</start>
<end>152</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MRC Examples Answerable by BERT without a Question Are Less Effective in MRC Model Training
%A Li, Hongyu
%A Chen, Tengyang
%A Bai, Shuting
%A Utsuro, Takehito
%A Kawada, Yasuhide
%Y Shmueli, Boaz
%Y Huang, Yin Jou
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F li-etal-2020-mrc
%X Models developed for Machine Reading Comprehension (MRC) are asked to predict an answer from a question and its related context. However, there exist cases that can be correctly answered by an MRC model using BERT, where only the context is provided without including the question. In this paper, these types of examples are referred to as “easy to answer”, while others are as “hard to answer”, i.e., unanswerable by an MRC model using BERT without being provided the question. Based on classifying examples as answerable or unanswerable by BERT without the given question, we propose a method based on BERT that splits the training examples from the MRC dataset SQuAD1.1 into those that are “easy to answer” or “hard to answer”. Experimental evaluation from a comparison of two models, one trained only with “easy to answer” examples and the other with “hard to answer” examples demonstrates that the latter outperforms the former.
%U https://aclanthology.org/2020.aacl-srw.21
%P 146-152
Markdown (Informal)
[MRC Examples Answerable by BERT without a Question Are Less Effective in MRC Model Training](https://aclanthology.org/2020.aacl-srw.21) (Li et al., AACL 2020)
ACL
- Hongyu Li, Tengyang Chen, Shuting Bai, Takehito Utsuro, and Yasuhide Kawada. 2020. MRC Examples Answerable by BERT without a Question Are Less Effective in MRC Model Training. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop, pages 146–152, Suzhou, China. Association for Computational Linguistics.