@inproceedings{longpre-etal-2019-exploration,
title = "An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering",
author = "Longpre, Shayne and
Lu, Yi and
Tu, Zhucheng and
DuBois, Chris",
editor = "Fisch, Adam and
Talmor, Alon and
Jia, Robin and
Seo, Minjoon and
Choi, Eunsol and
Chen, Danqi",
booktitle = "Proceedings of the 2nd Workshop on Machine Reading for Question Answering",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-5829",
doi = "10.18653/v1/D19-5829",
pages = "220--227",
abstract = "To produce a domain-agnostic question answering model for the Machine Reading Question Answering (MRQA) 2019 Shared Task, we investigate the relative benefits of large pre-trained language models, various data sampling strategies, as well as query and context paraphrases generated by back-translation. We find a simple negative sampling technique to be particularly effective, even though it is typically used for datasets that include unanswerable questions, such as SQuAD 2.0. When applied in conjunction with per-domain sampling, our XLNet (Yang et al., 2019)-based submission achieved the second best Exact Match and F1 in the MRQA leaderboard competition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="longpre-etal-2019-exploration">
<titleInfo>
<title>An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shayne</namePart>
<namePart type="family">Longpre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhucheng</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">DuBois</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Machine Reading for Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Fisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Talmor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjoon</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunsol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To produce a domain-agnostic question answering model for the Machine Reading Question Answering (MRQA) 2019 Shared Task, we investigate the relative benefits of large pre-trained language models, various data sampling strategies, as well as query and context paraphrases generated by back-translation. We find a simple negative sampling technique to be particularly effective, even though it is typically used for datasets that include unanswerable questions, such as SQuAD 2.0. When applied in conjunction with per-domain sampling, our XLNet (Yang et al., 2019)-based submission achieved the second best Exact Match and F1 in the MRQA leaderboard competition.</abstract>
<identifier type="citekey">longpre-etal-2019-exploration</identifier>
<identifier type="doi">10.18653/v1/D19-5829</identifier>
<location>
<url>https://aclanthology.org/D19-5829</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>220</start>
<end>227</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering
%A Longpre, Shayne
%A Lu, Yi
%A Tu, Zhucheng
%A DuBois, Chris
%Y Fisch, Adam
%Y Talmor, Alon
%Y Jia, Robin
%Y Seo, Minjoon
%Y Choi, Eunsol
%Y Chen, Danqi
%S Proceedings of the 2nd Workshop on Machine Reading for Question Answering
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F longpre-etal-2019-exploration
%X To produce a domain-agnostic question answering model for the Machine Reading Question Answering (MRQA) 2019 Shared Task, we investigate the relative benefits of large pre-trained language models, various data sampling strategies, as well as query and context paraphrases generated by back-translation. We find a simple negative sampling technique to be particularly effective, even though it is typically used for datasets that include unanswerable questions, such as SQuAD 2.0. When applied in conjunction with per-domain sampling, our XLNet (Yang et al., 2019)-based submission achieved the second best Exact Match and F1 in the MRQA leaderboard competition.
%R 10.18653/v1/D19-5829
%U https://aclanthology.org/D19-5829
%U https://doi.org/10.18653/v1/D19-5829
%P 220-227
Markdown (Informal)
[An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering](https://aclanthology.org/D19-5829) (Longpre et al., 2019)
ACL