@inproceedings{arroyo-etal-2020-multi,
title = "Multi-label classification of promotions in digital leaflets using textual and visual information",
author = "Arroyo, Roberto and
Jim{\'e}nez-Cabello, David and
Mart{\'\i}nez-Cebri{\'a}n, Javier",
editor = "Zhao, Huasha and
Sondhi, Parikshit and
Bach, Nguyen and
Hewavitharana, Sanjika and
He, Yifan and
Si, Luo and
Ji, Heng",
booktitle = "Proceedings of Workshop on Natural Language Processing in E-Commerce",
month = dec,
year = "2020",
address = "Barcelona, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.ecomnlp-1.2",
pages = "11--20",
abstract = "Product descriptions in e-commerce platforms contain detailed and valuable information about retailers assortment. In particular, coding promotions within digital leaflets are of great interest in e-commerce as they capture the attention of consumers by showing regular promotions for different products. However, this information is embedded into images, making it difficult to extract and process for downstream tasks. In this paper, we present an end-to-end approach that classifies promotions within digital leaflets into their corresponding product categories using both visual and textual information. Our approach can be divided into three key components: 1) region detection, 2) text recognition and 3) text classification. In many cases, a single promotion refers to multiple product categories, so we introduce a multi-label objective in the classification head. We demonstrate the effectiveness of our approach for two separated tasks: 1) image-based detection of the descriptions for each individual promotion and 2) multi-label classification of the product categories using the text from the product descriptions. We train and evaluate our models using a private dataset composed of images from digital leaflets obtained by Nielsen. Results show that we consistently outperform the proposed baseline by a large margin in all the experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arroyo-etal-2020-multi">
<titleInfo>
<title>Multi-label classification of promotions in digital leaflets using textual and visual information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Arroyo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jiménez-Cabello</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">Martínez-Cebrián</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Workshop on Natural Language Processing in E-Commerce</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huasha</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parikshit</namePart>
<namePart type="family">Sondhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nguyen</namePart>
<namePart type="family">Bach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjika</namePart>
<namePart type="family">Hewavitharana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luo</namePart>
<namePart type="family">Si</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Product descriptions in e-commerce platforms contain detailed and valuable information about retailers assortment. In particular, coding promotions within digital leaflets are of great interest in e-commerce as they capture the attention of consumers by showing regular promotions for different products. However, this information is embedded into images, making it difficult to extract and process for downstream tasks. In this paper, we present an end-to-end approach that classifies promotions within digital leaflets into their corresponding product categories using both visual and textual information. Our approach can be divided into three key components: 1) region detection, 2) text recognition and 3) text classification. In many cases, a single promotion refers to multiple product categories, so we introduce a multi-label objective in the classification head. We demonstrate the effectiveness of our approach for two separated tasks: 1) image-based detection of the descriptions for each individual promotion and 2) multi-label classification of the product categories using the text from the product descriptions. We train and evaluate our models using a private dataset composed of images from digital leaflets obtained by Nielsen. Results show that we consistently outperform the proposed baseline by a large margin in all the experiments.</abstract>
<identifier type="citekey">arroyo-etal-2020-multi</identifier>
<location>
<url>https://aclanthology.org/2020.ecomnlp-1.2</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>11</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-label classification of promotions in digital leaflets using textual and visual information
%A Arroyo, Roberto
%A Jiménez-Cabello, David
%A Martínez-Cebrián, Javier
%Y Zhao, Huasha
%Y Sondhi, Parikshit
%Y Bach, Nguyen
%Y Hewavitharana, Sanjika
%Y He, Yifan
%Y Si, Luo
%Y Ji, Heng
%S Proceedings of Workshop on Natural Language Processing in E-Commerce
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain
%F arroyo-etal-2020-multi
%X Product descriptions in e-commerce platforms contain detailed and valuable information about retailers assortment. In particular, coding promotions within digital leaflets are of great interest in e-commerce as they capture the attention of consumers by showing regular promotions for different products. However, this information is embedded into images, making it difficult to extract and process for downstream tasks. In this paper, we present an end-to-end approach that classifies promotions within digital leaflets into their corresponding product categories using both visual and textual information. Our approach can be divided into three key components: 1) region detection, 2) text recognition and 3) text classification. In many cases, a single promotion refers to multiple product categories, so we introduce a multi-label objective in the classification head. We demonstrate the effectiveness of our approach for two separated tasks: 1) image-based detection of the descriptions for each individual promotion and 2) multi-label classification of the product categories using the text from the product descriptions. We train and evaluate our models using a private dataset composed of images from digital leaflets obtained by Nielsen. Results show that we consistently outperform the proposed baseline by a large margin in all the experiments.
%U https://aclanthology.org/2020.ecomnlp-1.2
%P 11-20
Markdown (Informal)
[Multi-label classification of promotions in digital leaflets using textual and visual information](https://aclanthology.org/2020.ecomnlp-1.2) (Arroyo et al., EcomNLP 2020)
ACL