@inproceedings{tepper-etal-2020-balancing,
title = "Balancing via Generation for Multi-Class Text Classification Improvement",
author = "Tepper, Naama and
Goldbraich, Esther and
Zwerdling, Naama and
Kour, George and
Anaby Tavor, Ateret and
Carmeli, Boaz",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.130/",
doi = "10.18653/v1/2020.findings-emnlp.130",
pages = "1440--1452",
abstract = "Data balancing is a known technique for improving the performance of classification tasks. In this work we define a novel balancing-viageneration framework termed BalaGen. BalaGen consists of a flexible balancing policy coupled with a text generation mechanism. Combined, these two techniques can be used to augment a dataset for more balanced distribution. We evaluate BalaGen on three publicly available semantic utterance classification (SUC) datasets. One of these is a new COVID-19 Q{\&}A dataset published here for the first time. Our work demonstrates that optimal balancing policies can significantly improve classifier performance, while augmenting just part of the classes and under-sampling others. Furthermore, capitalizing on the advantages of balancing, we show its usefulness in all relevant BalaGen framework components. We validate the superiority of BalaGen on ten semantic utterance datasets taken from real-life goaloriented dialogue systems. Based on our results we encourage using data balancing prior to training for text classification tasks."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tepper-etal-2020-balancing">
<titleInfo>
<title>Balancing via Generation for Multi-Class Text Classification Improvement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naama</namePart>
<namePart type="family">Tepper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esther</namePart>
<namePart type="family">Goldbraich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naama</namePart>
<namePart type="family">Zwerdling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Kour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ateret</namePart>
<namePart type="family">Anaby Tavor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boaz</namePart>
<namePart type="family">Carmeli</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>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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 balancing is a known technique for improving the performance of classification tasks. In this work we define a novel balancing-viageneration framework termed BalaGen. BalaGen consists of a flexible balancing policy coupled with a text generation mechanism. Combined, these two techniques can be used to augment a dataset for more balanced distribution. We evaluate BalaGen on three publicly available semantic utterance classification (SUC) datasets. One of these is a new COVID-19 Q&A dataset published here for the first time. Our work demonstrates that optimal balancing policies can significantly improve classifier performance, while augmenting just part of the classes and under-sampling others. Furthermore, capitalizing on the advantages of balancing, we show its usefulness in all relevant BalaGen framework components. We validate the superiority of BalaGen on ten semantic utterance datasets taken from real-life goaloriented dialogue systems. Based on our results we encourage using data balancing prior to training for text classification tasks.</abstract>
<identifier type="citekey">tepper-etal-2020-balancing</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.130</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.130/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1440</start>
<end>1452</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Balancing via Generation for Multi-Class Text Classification Improvement
%A Tepper, Naama
%A Goldbraich, Esther
%A Zwerdling, Naama
%A Kour, George
%A Anaby Tavor, Ateret
%A Carmeli, Boaz
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F tepper-etal-2020-balancing
%X Data balancing is a known technique for improving the performance of classification tasks. In this work we define a novel balancing-viageneration framework termed BalaGen. BalaGen consists of a flexible balancing policy coupled with a text generation mechanism. Combined, these two techniques can be used to augment a dataset for more balanced distribution. We evaluate BalaGen on three publicly available semantic utterance classification (SUC) datasets. One of these is a new COVID-19 Q&A dataset published here for the first time. Our work demonstrates that optimal balancing policies can significantly improve classifier performance, while augmenting just part of the classes and under-sampling others. Furthermore, capitalizing on the advantages of balancing, we show its usefulness in all relevant BalaGen framework components. We validate the superiority of BalaGen on ten semantic utterance datasets taken from real-life goaloriented dialogue systems. Based on our results we encourage using data balancing prior to training for text classification tasks.
%R 10.18653/v1/2020.findings-emnlp.130
%U https://aclanthology.org/2020.findings-emnlp.130/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.130
%P 1440-1452
Markdown (Informal)
[Balancing via Generation for Multi-Class Text Classification Improvement](https://aclanthology.org/2020.findings-emnlp.130/) (Tepper et al., Findings 2020)
ACL