@inproceedings{yavuz-etal-2017-recovering,
title = "Recovering Question Answering Errors via Query Revision",
author = "Yavuz, Semih and
Gur, Izzeddin and
Su, Yu and
Yan, Xifeng",
editor = "Palmer, Martha and
Hwa, Rebecca and
Riedel, Sebastian",
booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D17-1094",
doi = "10.18653/v1/D17-1094",
pages = "903--909",
abstract = "The existing factoid QA systems often lack a post-inspection component that can help models recover from their own mistakes. In this work, we propose to crosscheck the corresponding KB relations behind the predicted answers and identify potential inconsistencies. Instead of developing a new model that accepts evidences collected from these relations, we choose to plug them back to the original questions directly and check if the revised question makes sense or not. A bidirectional LSTM is applied to encode revised questions. We develop a scoring mechanism over the revised question encodings to refine the predictions of a base QA system. This approach can improve the F1 score of STAGG (Yih et al., 2015), one of the leading QA systems, from 52.5{\%} to 53.9{\%} on WEBQUESTIONS data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yavuz-etal-2017-recovering">
<titleInfo>
<title>Recovering Question Answering Errors via Query Revision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Semih</namePart>
<namePart type="family">Yavuz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Izzeddin</namePart>
<namePart type="family">Gur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xifeng</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Riedel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The existing factoid QA systems often lack a post-inspection component that can help models recover from their own mistakes. In this work, we propose to crosscheck the corresponding KB relations behind the predicted answers and identify potential inconsistencies. Instead of developing a new model that accepts evidences collected from these relations, we choose to plug them back to the original questions directly and check if the revised question makes sense or not. A bidirectional LSTM is applied to encode revised questions. We develop a scoring mechanism over the revised question encodings to refine the predictions of a base QA system. This approach can improve the F1 score of STAGG (Yih et al., 2015), one of the leading QA systems, from 52.5% to 53.9% on WEBQUESTIONS data.</abstract>
<identifier type="citekey">yavuz-etal-2017-recovering</identifier>
<identifier type="doi">10.18653/v1/D17-1094</identifier>
<location>
<url>https://aclanthology.org/D17-1094</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>903</start>
<end>909</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recovering Question Answering Errors via Query Revision
%A Yavuz, Semih
%A Gur, Izzeddin
%A Su, Yu
%A Yan, Xifeng
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F yavuz-etal-2017-recovering
%X The existing factoid QA systems often lack a post-inspection component that can help models recover from their own mistakes. In this work, we propose to crosscheck the corresponding KB relations behind the predicted answers and identify potential inconsistencies. Instead of developing a new model that accepts evidences collected from these relations, we choose to plug them back to the original questions directly and check if the revised question makes sense or not. A bidirectional LSTM is applied to encode revised questions. We develop a scoring mechanism over the revised question encodings to refine the predictions of a base QA system. This approach can improve the F1 score of STAGG (Yih et al., 2015), one of the leading QA systems, from 52.5% to 53.9% on WEBQUESTIONS data.
%R 10.18653/v1/D17-1094
%U https://aclanthology.org/D17-1094
%U https://doi.org/10.18653/v1/D17-1094
%P 903-909
Markdown (Informal)
[Recovering Question Answering Errors via Query Revision](https://aclanthology.org/D17-1094) (Yavuz et al., EMNLP 2017)
ACL
- Semih Yavuz, Izzeddin Gur, Yu Su, and Xifeng Yan. 2017. Recovering Question Answering Errors via Query Revision. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 903–909, Copenhagen, Denmark. Association for Computational Linguistics.