@inproceedings{jia-etal-2023-kg,
title = "{KG}-{FLIP}: Knowledge-guided Fashion-domain Language-Image Pre-training for {E}-commerce",
author = "Jia, Qinjin and
Liu, Yang and
Wu, Daoping and
Xu, Shaoyuan and
Liu, Huidong and
Fu, Jinmiao and
Vollgraf, Roland and
Wang, Bryan",
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.9",
doi = "10.18653/v1/2023.acl-industry.9",
pages = "81--88",
abstract = "Various Vision-Language Pre-training (VLP) models (e.g., CLIP, BLIP) have sprung up and dramatically advanced the benchmarks for public general-domain datasets (e.g., COCO, Flickr30k). Such models usually learn the cross-modal alignment from large-scale well-aligned image-text datasets without leveraging external knowledge. Adapting these models to downstream applications in specific domains like fashion requires fine-grained in-domain image-text corpus, which are usually less semantically aligned and in small scale that requires efficient pre-training strategies. In this paper, we propose a knowledge-guided fashion-domain language-image pre-training (FLIP) framework that focuses on learning fine-grained representations in e-commerce domain and utilizes external knowledge (i.e., product attribute schema), to improve the pre-training efficiency. Experiments demonstrate that FLIP outperforms previous state-of-the-art VLP models on Amazon data and on the Fashion-Gen dataset by large margins. FLIP has been successfully deployed in the Amazon catalog system to backfill missing attributes and improve the customer shopping experience.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jia-etal-2023-kg">
<titleInfo>
<title>KG-FLIP: Knowledge-guided Fashion-domain Language-Image Pre-training for E-commerce</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qinjin</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daoping</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaoyuan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huidong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinmiao</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roland</namePart>
<namePart type="family">Vollgraf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Wang</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>Various Vision-Language Pre-training (VLP) models (e.g., CLIP, BLIP) have sprung up and dramatically advanced the benchmarks for public general-domain datasets (e.g., COCO, Flickr30k). Such models usually learn the cross-modal alignment from large-scale well-aligned image-text datasets without leveraging external knowledge. Adapting these models to downstream applications in specific domains like fashion requires fine-grained in-domain image-text corpus, which are usually less semantically aligned and in small scale that requires efficient pre-training strategies. In this paper, we propose a knowledge-guided fashion-domain language-image pre-training (FLIP) framework that focuses on learning fine-grained representations in e-commerce domain and utilizes external knowledge (i.e., product attribute schema), to improve the pre-training efficiency. Experiments demonstrate that FLIP outperforms previous state-of-the-art VLP models on Amazon data and on the Fashion-Gen dataset by large margins. FLIP has been successfully deployed in the Amazon catalog system to backfill missing attributes and improve the customer shopping experience.</abstract>
<identifier type="citekey">jia-etal-2023-kg</identifier>
<identifier type="doi">10.18653/v1/2023.acl-industry.9</identifier>
<location>
<url>https://aclanthology.org/2023.acl-industry.9</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>81</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KG-FLIP: Knowledge-guided Fashion-domain Language-Image Pre-training for E-commerce
%A Jia, Qinjin
%A Liu, Yang
%A Wu, Daoping
%A Xu, Shaoyuan
%A Liu, Huidong
%A Fu, Jinmiao
%A Vollgraf, Roland
%A Wang, Bryan
%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 jia-etal-2023-kg
%X Various Vision-Language Pre-training (VLP) models (e.g., CLIP, BLIP) have sprung up and dramatically advanced the benchmarks for public general-domain datasets (e.g., COCO, Flickr30k). Such models usually learn the cross-modal alignment from large-scale well-aligned image-text datasets without leveraging external knowledge. Adapting these models to downstream applications in specific domains like fashion requires fine-grained in-domain image-text corpus, which are usually less semantically aligned and in small scale that requires efficient pre-training strategies. In this paper, we propose a knowledge-guided fashion-domain language-image pre-training (FLIP) framework that focuses on learning fine-grained representations in e-commerce domain and utilizes external knowledge (i.e., product attribute schema), to improve the pre-training efficiency. Experiments demonstrate that FLIP outperforms previous state-of-the-art VLP models on Amazon data and on the Fashion-Gen dataset by large margins. FLIP has been successfully deployed in the Amazon catalog system to backfill missing attributes and improve the customer shopping experience.
%R 10.18653/v1/2023.acl-industry.9
%U https://aclanthology.org/2023.acl-industry.9
%U https://doi.org/10.18653/v1/2023.acl-industry.9
%P 81-88
Markdown (Informal)
[KG-FLIP: Knowledge-guided Fashion-domain Language-Image Pre-training for E-commerce](https://aclanthology.org/2023.acl-industry.9) (Jia et al., ACL 2023)
ACL
- Qinjin Jia, Yang Liu, Daoping Wu, Shaoyuan Xu, Huidong Liu, Jinmiao Fu, Roland Vollgraf, and Bryan Wang. 2023. KG-FLIP: Knowledge-guided Fashion-domain Language-Image Pre-training for E-commerce. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 81–88, Toronto, Canada. Association for Computational Linguistics.