@inproceedings{avigdor-etal-2023-consistent,
title = "Consistent Text Categorization using Data Augmentation in e-Commerce",
author = "Avigdor, Noa and
Horowitz, Guy and
Raviv, Ariel and
Yanovsky Daye, Stav",
editor = "Sitaram, Sunayana and
Beigman Klebanov, Beata and
Williams, Jason D",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-industry.30",
doi = "10.18653/v1/2023.acl-industry.30",
pages = "313--321",
abstract = "The categorization of massive e-Commerce data is a crucial, well-studied task, which is prevalent in industrial settings. In this work, we aim to improve an existing product categorization model that is already in use by a major web company, serving multiple applications. At its core, the product categorization model is a text classification model that takes a product title as an input and outputs the most suitable category out of thousands of available candidates. Upon a closer inspection, we found inconsistencies in the labeling of similar items. For example, minor modifications of the product title pertaining to colors or measurements majorly impacted the model{'}s output. This phenomenon can negatively affect downstream recommendation or search applications, leading to a sub-optimal user experience. To address this issue, we propose a new framework for consistent text categorization. Our goal is to improve the model{'}s consistency while maintaining its production-level performance. We use a semi-supervised approach for data augmentation and presents two different methods for utilizing unlabeled samples. One method relies directly on existing catalogs, while the other uses a generative model. We compare the pros and cons of each approach and present our experimental results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="avigdor-etal-2023-consistent">
<titleInfo>
<title>Consistent Text Categorization using Data Augmentation in e-Commerce</title>
</titleInfo>
<name type="personal">
<namePart type="given">Noa</namePart>
<namePart type="family">Avigdor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Horowitz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariel</namePart>
<namePart type="family">Raviv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stav</namePart>
<namePart type="family">Yanovsky Daye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Beigman Klebanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The categorization of massive e-Commerce data is a crucial, well-studied task, which is prevalent in industrial settings. In this work, we aim to improve an existing product categorization model that is already in use by a major web company, serving multiple applications. At its core, the product categorization model is a text classification model that takes a product title as an input and outputs the most suitable category out of thousands of available candidates. Upon a closer inspection, we found inconsistencies in the labeling of similar items. For example, minor modifications of the product title pertaining to colors or measurements majorly impacted the model’s output. This phenomenon can negatively affect downstream recommendation or search applications, leading to a sub-optimal user experience. To address this issue, we propose a new framework for consistent text categorization. Our goal is to improve the model’s consistency while maintaining its production-level performance. We use a semi-supervised approach for data augmentation and presents two different methods for utilizing unlabeled samples. One method relies directly on existing catalogs, while the other uses a generative model. We compare the pros and cons of each approach and present our experimental results.</abstract>
<identifier type="citekey">avigdor-etal-2023-consistent</identifier>
<identifier type="doi">10.18653/v1/2023.acl-industry.30</identifier>
<location>
<url>https://aclanthology.org/2023.acl-industry.30</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>313</start>
<end>321</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Consistent Text Categorization using Data Augmentation in e-Commerce
%A Avigdor, Noa
%A Horowitz, Guy
%A Raviv, Ariel
%A Yanovsky Daye, Stav
%Y Sitaram, Sunayana
%Y Beigman Klebanov, Beata
%Y Williams, Jason D.
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F avigdor-etal-2023-consistent
%X The categorization of massive e-Commerce data is a crucial, well-studied task, which is prevalent in industrial settings. In this work, we aim to improve an existing product categorization model that is already in use by a major web company, serving multiple applications. At its core, the product categorization model is a text classification model that takes a product title as an input and outputs the most suitable category out of thousands of available candidates. Upon a closer inspection, we found inconsistencies in the labeling of similar items. For example, minor modifications of the product title pertaining to colors or measurements majorly impacted the model’s output. This phenomenon can negatively affect downstream recommendation or search applications, leading to a sub-optimal user experience. To address this issue, we propose a new framework for consistent text categorization. Our goal is to improve the model’s consistency while maintaining its production-level performance. We use a semi-supervised approach for data augmentation and presents two different methods for utilizing unlabeled samples. One method relies directly on existing catalogs, while the other uses a generative model. We compare the pros and cons of each approach and present our experimental results.
%R 10.18653/v1/2023.acl-industry.30
%U https://aclanthology.org/2023.acl-industry.30
%U https://doi.org/10.18653/v1/2023.acl-industry.30
%P 313-321
Markdown (Informal)
[Consistent Text Categorization using Data Augmentation in e-Commerce](https://aclanthology.org/2023.acl-industry.30) (Avigdor et al., ACL 2023)
ACL