@inproceedings{jin-etal-2018-using,
title = "Using Paraphrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Patient Dialogue System",
author = "Jin, Lifeng and
King, David and
Hussein, Amad and
White, Michael and
Danforth, Douglas",
editor = "Tetreault, Joel and
Burstein, Jill and
Kochmar, Ekaterina and
Leacock, Claudia and
Yannakoudakis, Helen",
booktitle = "Proceedings of the Thirteenth Workshop on Innovative Use of {NLP} for Building Educational Applications",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-0502",
doi = "10.18653/v1/W18-0502",
pages = "13--23",
abstract = "When interpreting questions in a virtual patient dialogue system one must inevitably tackle the challenge of a long tail of relatively infrequently asked questions. To make progress on this challenge, we investigate the use of paraphrasing for data augmentation and neural memory-based classification, finding that the two methods work best in combination. In particular, we find that the neural memory-based approach not only outperforms a straight CNN classifier on low frequency questions, but also takes better advantage of the augmented data created by paraphrasing, together yielding a nearly 10{\%} absolute improvement in accuracy on the least frequently asked questions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2018-using">
<titleInfo>
<title>Using Paraphrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Patient Dialogue System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">King</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amad</namePart>
<namePart type="family">Hussein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">White</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="family">Danforth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When interpreting questions in a virtual patient dialogue system one must inevitably tackle the challenge of a long tail of relatively infrequently asked questions. To make progress on this challenge, we investigate the use of paraphrasing for data augmentation and neural memory-based classification, finding that the two methods work best in combination. In particular, we find that the neural memory-based approach not only outperforms a straight CNN classifier on low frequency questions, but also takes better advantage of the augmented data created by paraphrasing, together yielding a nearly 10% absolute improvement in accuracy on the least frequently asked questions.</abstract>
<identifier type="citekey">jin-etal-2018-using</identifier>
<identifier type="doi">10.18653/v1/W18-0502</identifier>
<location>
<url>https://aclanthology.org/W18-0502</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>13</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Paraphrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Patient Dialogue System
%A Jin, Lifeng
%A King, David
%A Hussein, Amad
%A White, Michael
%A Danforth, Douglas
%Y Tetreault, Joel
%Y Burstein, Jill
%Y Kochmar, Ekaterina
%Y Leacock, Claudia
%Y Yannakoudakis, Helen
%S Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F jin-etal-2018-using
%X When interpreting questions in a virtual patient dialogue system one must inevitably tackle the challenge of a long tail of relatively infrequently asked questions. To make progress on this challenge, we investigate the use of paraphrasing for data augmentation and neural memory-based classification, finding that the two methods work best in combination. In particular, we find that the neural memory-based approach not only outperforms a straight CNN classifier on low frequency questions, but also takes better advantage of the augmented data created by paraphrasing, together yielding a nearly 10% absolute improvement in accuracy on the least frequently asked questions.
%R 10.18653/v1/W18-0502
%U https://aclanthology.org/W18-0502
%U https://doi.org/10.18653/v1/W18-0502
%P 13-23
Markdown (Informal)
[Using Paraphrasing and Memory-Augmented Models to Combat Data Sparsity in Question Interpretation with a Virtual Patient Dialogue System](https://aclanthology.org/W18-0502) (Jin et al., BEA 2018)
ACL