@inproceedings{fearn-etal-2021-exploring,
title = "Exploring the Relationship Between Algorithm Performance, Vocabulary, and Run-Time in Text Classification",
author = "Fearn, Wilson and
Weller, Orion and
Seppi, Kevin",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.244",
doi = "10.18653/v1/2021.naacl-main.244",
pages = "3069--3082",
abstract = "Text classification is a significant branch of natural language processing, and has many applications including document classification and sentiment analysis. Unsurprisingly, those who do text classification are concerned with the run-time of their algorithms, many of which depend on the size of the corpus{'} vocabulary due to their bag-of-words representation. Although many studies have examined the effect of preprocessing techniques on vocabulary size and accuracy, none have examined how these methods affect a model{'}s run-time. To fill this gap, we provide a comprehensive study that examines how preprocessing techniques affect the vocabulary size, model performance, and model run-time, evaluating ten techniques over four models and two datasets. We show that some individual methods can reduce run-time with no loss of accuracy, while some combinations of methods can trade 2-5{\%} of the accuracy for up to a 65{\%} reduction of run-time. Furthermore, some combinations of preprocessing techniques can even provide a 15{\%} reduction in run-time while simultaneously improving model accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fearn-etal-2021-exploring">
<titleInfo>
<title>Exploring the Relationship Between Algorithm Performance, Vocabulary, and Run-Time in Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wilson</namePart>
<namePart type="family">Fearn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orion</namePart>
<namePart type="family">Weller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Seppi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text classification is a significant branch of natural language processing, and has many applications including document classification and sentiment analysis. Unsurprisingly, those who do text classification are concerned with the run-time of their algorithms, many of which depend on the size of the corpus’ vocabulary due to their bag-of-words representation. Although many studies have examined the effect of preprocessing techniques on vocabulary size and accuracy, none have examined how these methods affect a model’s run-time. To fill this gap, we provide a comprehensive study that examines how preprocessing techniques affect the vocabulary size, model performance, and model run-time, evaluating ten techniques over four models and two datasets. We show that some individual methods can reduce run-time with no loss of accuracy, while some combinations of methods can trade 2-5% of the accuracy for up to a 65% reduction of run-time. Furthermore, some combinations of preprocessing techniques can even provide a 15% reduction in run-time while simultaneously improving model accuracy.</abstract>
<identifier type="citekey">fearn-etal-2021-exploring</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.244</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.244</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>3069</start>
<end>3082</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Relationship Between Algorithm Performance, Vocabulary, and Run-Time in Text Classification
%A Fearn, Wilson
%A Weller, Orion
%A Seppi, Kevin
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F fearn-etal-2021-exploring
%X Text classification is a significant branch of natural language processing, and has many applications including document classification and sentiment analysis. Unsurprisingly, those who do text classification are concerned with the run-time of their algorithms, many of which depend on the size of the corpus’ vocabulary due to their bag-of-words representation. Although many studies have examined the effect of preprocessing techniques on vocabulary size and accuracy, none have examined how these methods affect a model’s run-time. To fill this gap, we provide a comprehensive study that examines how preprocessing techniques affect the vocabulary size, model performance, and model run-time, evaluating ten techniques over four models and two datasets. We show that some individual methods can reduce run-time with no loss of accuracy, while some combinations of methods can trade 2-5% of the accuracy for up to a 65% reduction of run-time. Furthermore, some combinations of preprocessing techniques can even provide a 15% reduction in run-time while simultaneously improving model accuracy.
%R 10.18653/v1/2021.naacl-main.244
%U https://aclanthology.org/2021.naacl-main.244
%U https://doi.org/10.18653/v1/2021.naacl-main.244
%P 3069-3082
Markdown (Informal)
[Exploring the Relationship Between Algorithm Performance, Vocabulary, and Run-Time in Text Classification](https://aclanthology.org/2021.naacl-main.244) (Fearn et al., NAACL 2021)
ACL