<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T20:33:25Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/16113" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/16113</identifier><datestamp>2025-03-26T23:33:31Z</datestamp><setSpec>com_10012_9924</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9930</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">van Beek, Peter</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="278b460b-ae33-427a-8374-d1a568db4021" confidence="600">Tamming, Daniel</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2020-08-12T17:14:37Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2020-08-12T17:14:37Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2020-08-12</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2020-08-04</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/16113</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">Thanks to increases in computing power and the growing availability of large datasets,&#xd;
neural networks have achieved state of the art results in many natural language process-&#xd;
ing (NLP) and computer vision (CV) tasks. These models require a large number of&#xd;
training examples that are balanced between classes, but in many application areas they&#xd;
rely on training sets that are either small or imbalanced, or both. To address this, data&#xd;
augmentation has become standard practice in CV. This research is motivated by the ob-&#xd;
servation that, relative to CV, data augmentation is underused and understudied in NLP.&#xd;
Three methods of data augmentation are implemented and tested: synonym replacement,&#xd;
backtranslation, and contextual augmentation. Tests are conducted with two models: a&#xd;
Recurrent Neural Network (RNN) and Bidirectional Encoder Representations from Trans-&#xd;
formers (BERT). To develop learning curves and study the ability of augmentation methods&#xd;
to rebalance datasets, each of three binary classification datasets are made artificially small&#xd;
and made artificially imbalanced. The results show that these augmentation methods can&#xd;
offer accuracy improvements of over 1% to models with a baseline accuracy as high as&#xd;
92%. On the two largest datasets, the accuracy of BERT is usually improved by either&#xd;
synonym replacement or backtranslation, while the accuracy of the RNN is usually im-&#xd;
proved by all three augmentation techniques. The augmentation techniques tend to yield&#xd;
the largest accuracy boost when the datasets are smallest or most imbalanced; the per-&#xd;
formance benefits appear to converge to 0% as the dataset becomes larger. The optimal&#xd;
augmentation distance, the extent to which augmented training examples tend to deviate&#xd;
from their original form, decreases as datasets become more balanced. The results show&#xd;
that data augmentation is a powerful method of improving performance when training on&#xd;
datasets with fewer than 10,000 training examples. The accuracy increases that they offer&#xd;
are reduced by recent advancements in transfer learning schemes, but they are certainly&#xd;
not eliminated.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Data Augmentation For Text Classification Tasks</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Master Thesis</dim:field>
   <dim:field mdschema="dc" element="pending">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department" lang="en">David R. Cheriton School of Computer Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline" lang="en">Computer Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="grantor" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="uws-etd" element="degree" lang="en">Master of Mathematics</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">van Beek, Peter</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="affiliation1" lang="en">Faculty of Mathematics</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="city" lang="en">Waterloo</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="country" lang="en">Canada</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="province" lang="en">Ontario</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>