@inproceedings{zhang-etal-2023-pay,
title = "Pay Attention to Implicit Attribute Values: A Multi-modal Generative Framework for {AVE} Task",
author = "Zhang, Yupeng and
Wang, Shensi and
Li, Peiguang and
Dong, Guanting and
Wang, Sirui and
Xian, Yunsen and
Li, Zhoujun and
Zhang, Hongzhi",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.831",
doi = "10.18653/v1/2023.findings-acl.831",
pages = "13139--13151",
abstract = "Attribute Value Extraction (AVE) boosts many e-commerce platform services such as targeted recommendation, product retrieval and question answering. Most previous studies adopt an extractive framework such as named entity recognition (NER) to capture subtokens in the product descriptions as the corresponding values of target attributes. However, in the real world scenario, there also exist implicit attribute values that are not mentioned explicitly but embedded in the image information and implied text meaning of products, for which the power of extractive methods is severely constrained. To address the above issues, we exploit a unified multi-modal AVE framework named DEFLATE (a multi-modal unifieD framEwork For impLicit And expliciT AVE) to acquire implicit attribute values in addition to the explicit ones. DEFLATE consists of a QA-based generation model to produce candidate attribute values from the product information of different modalities, and a discriminative model to ensure the credibility of the generated answers. Meanwhile, to provide a testbed that close to the real world, we collect and annotate a multi-modal dataset with parts of implicit attribute values. Extensive experiments conducted on multiple datasets demonstrate that DEFLATE significantly outperforms previous methods on the extraction of implicit attribute values, while achieving comparable performance for the explicit ones.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-pay">
<titleInfo>
<title>Pay Attention to Implicit Attribute Values: A Multi-modal Generative Framework for AVE Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yupeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shensi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peiguang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanting</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunsen</namePart>
<namePart type="family">Xian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhoujun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongzhi</namePart>
<namePart type="family">Zhang</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>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</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>Attribute Value Extraction (AVE) boosts many e-commerce platform services such as targeted recommendation, product retrieval and question answering. Most previous studies adopt an extractive framework such as named entity recognition (NER) to capture subtokens in the product descriptions as the corresponding values of target attributes. However, in the real world scenario, there also exist implicit attribute values that are not mentioned explicitly but embedded in the image information and implied text meaning of products, for which the power of extractive methods is severely constrained. To address the above issues, we exploit a unified multi-modal AVE framework named DEFLATE (a multi-modal unifieD framEwork For impLicit And expliciT AVE) to acquire implicit attribute values in addition to the explicit ones. DEFLATE consists of a QA-based generation model to produce candidate attribute values from the product information of different modalities, and a discriminative model to ensure the credibility of the generated answers. Meanwhile, to provide a testbed that close to the real world, we collect and annotate a multi-modal dataset with parts of implicit attribute values. Extensive experiments conducted on multiple datasets demonstrate that DEFLATE significantly outperforms previous methods on the extraction of implicit attribute values, while achieving comparable performance for the explicit ones.</abstract>
<identifier type="citekey">zhang-etal-2023-pay</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.831</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.831</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>13139</start>
<end>13151</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pay Attention to Implicit Attribute Values: A Multi-modal Generative Framework for AVE Task
%A Zhang, Yupeng
%A Wang, Shensi
%A Li, Peiguang
%A Dong, Guanting
%A Wang, Sirui
%A Xian, Yunsen
%A Li, Zhoujun
%A Zhang, Hongzhi
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zhang-etal-2023-pay
%X Attribute Value Extraction (AVE) boosts many e-commerce platform services such as targeted recommendation, product retrieval and question answering. Most previous studies adopt an extractive framework such as named entity recognition (NER) to capture subtokens in the product descriptions as the corresponding values of target attributes. However, in the real world scenario, there also exist implicit attribute values that are not mentioned explicitly but embedded in the image information and implied text meaning of products, for which the power of extractive methods is severely constrained. To address the above issues, we exploit a unified multi-modal AVE framework named DEFLATE (a multi-modal unifieD framEwork For impLicit And expliciT AVE) to acquire implicit attribute values in addition to the explicit ones. DEFLATE consists of a QA-based generation model to produce candidate attribute values from the product information of different modalities, and a discriminative model to ensure the credibility of the generated answers. Meanwhile, to provide a testbed that close to the real world, we collect and annotate a multi-modal dataset with parts of implicit attribute values. Extensive experiments conducted on multiple datasets demonstrate that DEFLATE significantly outperforms previous methods on the extraction of implicit attribute values, while achieving comparable performance for the explicit ones.
%R 10.18653/v1/2023.findings-acl.831
%U https://aclanthology.org/2023.findings-acl.831
%U https://doi.org/10.18653/v1/2023.findings-acl.831
%P 13139-13151
Markdown (Informal)
[Pay Attention to Implicit Attribute Values: A Multi-modal Generative Framework for AVE Task](https://aclanthology.org/2023.findings-acl.831) (Zhang et al., Findings 2023)
ACL
- Yupeng Zhang, Shensi Wang, Peiguang Li, Guanting Dong, Sirui Wang, Yunsen Xian, Zhoujun Li, and Hongzhi Zhang. 2023. Pay Attention to Implicit Attribute Values: A Multi-modal Generative Framework for AVE Task. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13139–13151, Toronto, Canada. Association for Computational Linguistics.