@inproceedings{chen-chou-2022-utilizing,
title = "Utilizing Cross-Modal Contrastive Learning to Improve Item Categorization {BERT} Model",
author = "Chen, Lei and
Chou, Hou Wei",
editor = "Malmasi, Shervin and
Rokhlenko, Oleg and
Ueffing, Nicola and
Guy, Ido and
Agichtein, Eugene and
Kallumadi, Surya",
booktitle = "Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.ecnlp-1.25",
doi = "10.18653/v1/2022.ecnlp-1.25",
pages = "217--223",
abstract = "Item categorization (IC) is a core natural language processing (NLP) task in e-commerce. As a special text classification task, fine-tuning pre-trained models, e.g., BERT, has become a mainstream solution. To improve IC performance further, other product metadata, e.g., product images, have been used. Although multimodal IC (MIC) systems show higher performance, expanding from processing text to more resource-demanding images brings large engineering impacts and hinders the deployment of such dual-input MIC systems. In this paper, we proposed a new way of using product images to improve text-only IC model: leveraging cross-modal signals between products{'} titles and associated images to adapt BERT models in a self-supervised learning (SSL) way. Our experiments on the three genres in the public Amazon product dataset show that the proposed method generates improved prediction accuracy and macro-F1 values than simply using the original BERT. Moreover, the proposed method is able to keep using existing text-only IC inference implementation and shows a resource advantage than the deployment of a dual-input MIC system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-chou-2022-utilizing">
<titleInfo>
<title>Utilizing Cross-Modal Contrastive Learning to Improve Item Categorization BERT Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hou</namePart>
<namePart type="given">Wei</namePart>
<namePart type="family">Chou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Rokhlenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicola</namePart>
<namePart type="family">Ueffing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Guy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Agichtein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surya</namePart>
<namePart type="family">Kallumadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Item categorization (IC) is a core natural language processing (NLP) task in e-commerce. As a special text classification task, fine-tuning pre-trained models, e.g., BERT, has become a mainstream solution. To improve IC performance further, other product metadata, e.g., product images, have been used. Although multimodal IC (MIC) systems show higher performance, expanding from processing text to more resource-demanding images brings large engineering impacts and hinders the deployment of such dual-input MIC systems. In this paper, we proposed a new way of using product images to improve text-only IC model: leveraging cross-modal signals between products’ titles and associated images to adapt BERT models in a self-supervised learning (SSL) way. Our experiments on the three genres in the public Amazon product dataset show that the proposed method generates improved prediction accuracy and macro-F1 values than simply using the original BERT. Moreover, the proposed method is able to keep using existing text-only IC inference implementation and shows a resource advantage than the deployment of a dual-input MIC system.</abstract>
<identifier type="citekey">chen-chou-2022-utilizing</identifier>
<identifier type="doi">10.18653/v1/2022.ecnlp-1.25</identifier>
<location>
<url>https://aclanthology.org/2022.ecnlp-1.25</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>217</start>
<end>223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Utilizing Cross-Modal Contrastive Learning to Improve Item Categorization BERT Model
%A Chen, Lei
%A Chou, Hou Wei
%Y Malmasi, Shervin
%Y Rokhlenko, Oleg
%Y Ueffing, Nicola
%Y Guy, Ido
%Y Agichtein, Eugene
%Y Kallumadi, Surya
%S Proceedings of the Fifth Workshop on e-Commerce and NLP (ECNLP 5)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F chen-chou-2022-utilizing
%X Item categorization (IC) is a core natural language processing (NLP) task in e-commerce. As a special text classification task, fine-tuning pre-trained models, e.g., BERT, has become a mainstream solution. To improve IC performance further, other product metadata, e.g., product images, have been used. Although multimodal IC (MIC) systems show higher performance, expanding from processing text to more resource-demanding images brings large engineering impacts and hinders the deployment of such dual-input MIC systems. In this paper, we proposed a new way of using product images to improve text-only IC model: leveraging cross-modal signals between products’ titles and associated images to adapt BERT models in a self-supervised learning (SSL) way. Our experiments on the three genres in the public Amazon product dataset show that the proposed method generates improved prediction accuracy and macro-F1 values than simply using the original BERT. Moreover, the proposed method is able to keep using existing text-only IC inference implementation and shows a resource advantage than the deployment of a dual-input MIC system.
%R 10.18653/v1/2022.ecnlp-1.25
%U https://aclanthology.org/2022.ecnlp-1.25
%U https://doi.org/10.18653/v1/2022.ecnlp-1.25
%P 217-223
Markdown (Informal)
[Utilizing Cross-Modal Contrastive Learning to Improve Item Categorization BERT Model](https://aclanthology.org/2022.ecnlp-1.25) (Chen & Chou, ECNLP 2022)
ACL