@inproceedings{gong-etal-2025-visual,
title = "Visual Zero-Shot {E}-Commerce Product Attribute Value Extraction",
author = "Gong, Jiaying and
Cheng, Ming and
Shen, Hongda and
Vandenbussche, Pierre-Yves and
Jenq, Janet and
Eldardiry, Hoda",
editor = "Chen, Weizhu and
Yang, Yi and
Kachuee, Mohammad and
Fu, Xue-Yong",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-industry.38/",
doi = "10.18653/v1/2025.naacl-industry.38",
pages = "460--469",
ISBN = "979-8-89176-194-0",
abstract = "Existing zero-shot product attribute value (aspect) extraction approaches in e-Commerce industry rely on uni-modal or multi-modal models, where the sellers are asked to provide detailed textual inputs (product descriptions) for the products. However, manually providing (typing) the product descriptions is time-consuming and frustrating for the sellers. Thus, we propose a cross-modal zero-shot attribute value generation framework (ViOC-AG) based on CLIP, which only requires product images as the inputs. ViOC-AG follows a text-only training process, where a task-customized text decoder is trained with the frozen CLIP text encoder to alleviate the modality gap and task disconnection. During the zero-shot inference, product aspects are generated by the frozen CLIP image encoder connected with the trained task-customized text decoder. OCR tokens and outputs from a frozen prompt-based LLM correct the decoded outputs for out-of-domain attribute values. Experiments show that ViOC-AG significantly outperforms other fine-tuned vision-language models for zero-shot attribute value extraction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gong-etal-2025-visual">
<titleInfo>
<title>Visual Zero-Shot E-Commerce Product Attribute Value Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaying</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongda</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre-Yves</namePart>
<namePart type="family">Vandenbussche</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janet</namePart>
<namePart type="family">Jenq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hoda</namePart>
<namePart type="family">Eldardiry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weizhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Kachuee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue-Yong</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-194-0</identifier>
</relatedItem>
<abstract>Existing zero-shot product attribute value (aspect) extraction approaches in e-Commerce industry rely on uni-modal or multi-modal models, where the sellers are asked to provide detailed textual inputs (product descriptions) for the products. However, manually providing (typing) the product descriptions is time-consuming and frustrating for the sellers. Thus, we propose a cross-modal zero-shot attribute value generation framework (ViOC-AG) based on CLIP, which only requires product images as the inputs. ViOC-AG follows a text-only training process, where a task-customized text decoder is trained with the frozen CLIP text encoder to alleviate the modality gap and task disconnection. During the zero-shot inference, product aspects are generated by the frozen CLIP image encoder connected with the trained task-customized text decoder. OCR tokens and outputs from a frozen prompt-based LLM correct the decoded outputs for out-of-domain attribute values. Experiments show that ViOC-AG significantly outperforms other fine-tuned vision-language models for zero-shot attribute value extraction.</abstract>
<identifier type="citekey">gong-etal-2025-visual</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-industry.38</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-industry.38/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>460</start>
<end>469</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visual Zero-Shot E-Commerce Product Attribute Value Extraction
%A Gong, Jiaying
%A Cheng, Ming
%A Shen, Hongda
%A Vandenbussche, Pierre-Yves
%A Jenq, Janet
%A Eldardiry, Hoda
%Y Chen, Weizhu
%Y Yang, Yi
%Y Kachuee, Mohammad
%Y Fu, Xue-Yong
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-194-0
%F gong-etal-2025-visual
%X Existing zero-shot product attribute value (aspect) extraction approaches in e-Commerce industry rely on uni-modal or multi-modal models, where the sellers are asked to provide detailed textual inputs (product descriptions) for the products. However, manually providing (typing) the product descriptions is time-consuming and frustrating for the sellers. Thus, we propose a cross-modal zero-shot attribute value generation framework (ViOC-AG) based on CLIP, which only requires product images as the inputs. ViOC-AG follows a text-only training process, where a task-customized text decoder is trained with the frozen CLIP text encoder to alleviate the modality gap and task disconnection. During the zero-shot inference, product aspects are generated by the frozen CLIP image encoder connected with the trained task-customized text decoder. OCR tokens and outputs from a frozen prompt-based LLM correct the decoded outputs for out-of-domain attribute values. Experiments show that ViOC-AG significantly outperforms other fine-tuned vision-language models for zero-shot attribute value extraction.
%R 10.18653/v1/2025.naacl-industry.38
%U https://aclanthology.org/2025.naacl-industry.38/
%U https://doi.org/10.18653/v1/2025.naacl-industry.38
%P 460-469
Markdown (Informal)
[Visual Zero-Shot E-Commerce Product Attribute Value Extraction](https://aclanthology.org/2025.naacl-industry.38/) (Gong et al., NAACL 2025)
ACL
- Jiaying Gong, Ming Cheng, Hongda Shen, Pierre-Yves Vandenbussche, Janet Jenq, and Hoda Eldardiry. 2025. Visual Zero-Shot E-Commerce Product Attribute Value Extraction. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track), pages 460–469, Albuquerque, New Mexico. Association for Computational Linguistics.