@inproceedings{kashefi-hwa-2020-quantifying,
title = "Quantifying the Evaluation of Heuristic Methods for Textual Data Augmentation",
author = "Kashefi, Omid and
Hwa, Rebecca",
editor = "Xu, Wei and
Ritter, Alan and
Baldwin, Tim and
Rahimi, Afshin",
booktitle = "Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wnut-1.26",
doi = "10.18653/v1/2020.wnut-1.26",
pages = "200--208",
abstract = "Data augmentation has been shown to be effective in providing more training data for machine learning and resulting in more robust classifiers. However, for some problems, there may be multiple augmentation heuristics, and the choices of which one to use may significantly impact the success of the training. In this work, we propose a metric for evaluating augmentation heuristics; specifically, we quantify the extent to which an example is {``}hard to distinguish{''} by considering the difference between the distribution of the augmented samples of different classes. Experimenting with multiple heuristics in two prediction tasks (positive/negative sentiment and verbosity/conciseness) validates our claims by revealing the connection between the distribution difference of different classes and the classification accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kashefi-hwa-2020-quantifying">
<titleInfo>
<title>Quantifying the Evaluation of Heuristic Methods for Textual Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Omid</namePart>
<namePart type="family">Kashefi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</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>Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</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>Data augmentation has been shown to be effective in providing more training data for machine learning and resulting in more robust classifiers. However, for some problems, there may be multiple augmentation heuristics, and the choices of which one to use may significantly impact the success of the training. In this work, we propose a metric for evaluating augmentation heuristics; specifically, we quantify the extent to which an example is “hard to distinguish” by considering the difference between the distribution of the augmented samples of different classes. Experimenting with multiple heuristics in two prediction tasks (positive/negative sentiment and verbosity/conciseness) validates our claims by revealing the connection between the distribution difference of different classes and the classification accuracy.</abstract>
<identifier type="citekey">kashefi-hwa-2020-quantifying</identifier>
<identifier type="doi">10.18653/v1/2020.wnut-1.26</identifier>
<location>
<url>https://aclanthology.org/2020.wnut-1.26</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>200</start>
<end>208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quantifying the Evaluation of Heuristic Methods for Textual Data Augmentation
%A Kashefi, Omid
%A Hwa, Rebecca
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%Y Rahimi, Afshin
%S Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F kashefi-hwa-2020-quantifying
%X Data augmentation has been shown to be effective in providing more training data for machine learning and resulting in more robust classifiers. However, for some problems, there may be multiple augmentation heuristics, and the choices of which one to use may significantly impact the success of the training. In this work, we propose a metric for evaluating augmentation heuristics; specifically, we quantify the extent to which an example is “hard to distinguish” by considering the difference between the distribution of the augmented samples of different classes. Experimenting with multiple heuristics in two prediction tasks (positive/negative sentiment and verbosity/conciseness) validates our claims by revealing the connection between the distribution difference of different classes and the classification accuracy.
%R 10.18653/v1/2020.wnut-1.26
%U https://aclanthology.org/2020.wnut-1.26
%U https://doi.org/10.18653/v1/2020.wnut-1.26
%P 200-208
Markdown (Informal)
[Quantifying the Evaluation of Heuristic Methods for Textual Data Augmentation](https://aclanthology.org/2020.wnut-1.26) (Kashefi & Hwa, WNUT 2020)
ACL