@inproceedings{liu-etal-2023-knowledge,
title = "Knowledge-Selective Pretraining for Attribute Value Extraction",
author = "Liu, Hui and
Yin, Qingyu and
Wang, Zhengyang and
Zhang, Chenwei and
Jiang, Haoming and
Gao, Yifan and
Li, Zheng and
Li, Xian and
Zhang, Chao and
Yin, Bing and
Wang, William and
Zhu, Xiaodan",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.542",
doi = "10.18653/v1/2023.findings-emnlp.542",
pages = "8062--8074",
abstract = "Attribute Value Extraction (AVE) aims to retrieve the values of attributes from the product profiles. The state-of-the-art methods tackle the AVE task through a question-answering (QA) paradigm, where the value is predicted from the context (i.e. product profile) given a query (i.e. attributes). Despite of the substantial advancements that have been made, the performance of existing methods on rare attributes is still far from satisfaction, and they cannot be easily extended to unseen attributes due to the poor generalization ability. In this work, we propose to leverage pretraining and transfer learning to address the aforementioned weaknesses. We first collect the product information from various E-commerce stores and retrieve a large number of (profile, attribute, value) triples, which will be used as the pretraining corpus. To more effectively utilize the retrieved corpus, we further design a Knowledge-Selective Framework (KSelF) based on query expansion that can be closely combined with the pretraining corpus to boost the performance. Meanwhile, considering the public AE-pub dataset contains considerable noise, we construct and contribute a larger benchmark EC-AVE collected from E-commerce websites. We conduct evaluation on both of these datasets. The experimental results demonstrate that our proposed KSelF achieves new state-of-the-art performance without pretraining. When incorporated with the pretraining corpus, the performance of KSelF can be further improved, particularly on the attributes with limited training resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2023-knowledge">
<titleInfo>
<title>Knowledge-Selective Pretraining for Attribute Value Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingyu</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenwei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoming</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Attribute Value Extraction (AVE) aims to retrieve the values of attributes from the product profiles. The state-of-the-art methods tackle the AVE task through a question-answering (QA) paradigm, where the value is predicted from the context (i.e. product profile) given a query (i.e. attributes). Despite of the substantial advancements that have been made, the performance of existing methods on rare attributes is still far from satisfaction, and they cannot be easily extended to unseen attributes due to the poor generalization ability. In this work, we propose to leverage pretraining and transfer learning to address the aforementioned weaknesses. We first collect the product information from various E-commerce stores and retrieve a large number of (profile, attribute, value) triples, which will be used as the pretraining corpus. To more effectively utilize the retrieved corpus, we further design a Knowledge-Selective Framework (KSelF) based on query expansion that can be closely combined with the pretraining corpus to boost the performance. Meanwhile, considering the public AE-pub dataset contains considerable noise, we construct and contribute a larger benchmark EC-AVE collected from E-commerce websites. We conduct evaluation on both of these datasets. The experimental results demonstrate that our proposed KSelF achieves new state-of-the-art performance without pretraining. When incorporated with the pretraining corpus, the performance of KSelF can be further improved, particularly on the attributes with limited training resources.</abstract>
<identifier type="citekey">liu-etal-2023-knowledge</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.542</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.542</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>8062</start>
<end>8074</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge-Selective Pretraining for Attribute Value Extraction
%A Liu, Hui
%A Yin, Qingyu
%A Wang, Zhengyang
%A Zhang, Chenwei
%A Jiang, Haoming
%A Gao, Yifan
%A Li, Zheng
%A Li, Xian
%A Zhang, Chao
%A Yin, Bing
%A Wang, William
%A Zhu, Xiaodan
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F liu-etal-2023-knowledge
%X Attribute Value Extraction (AVE) aims to retrieve the values of attributes from the product profiles. The state-of-the-art methods tackle the AVE task through a question-answering (QA) paradigm, where the value is predicted from the context (i.e. product profile) given a query (i.e. attributes). Despite of the substantial advancements that have been made, the performance of existing methods on rare attributes is still far from satisfaction, and they cannot be easily extended to unseen attributes due to the poor generalization ability. In this work, we propose to leverage pretraining and transfer learning to address the aforementioned weaknesses. We first collect the product information from various E-commerce stores and retrieve a large number of (profile, attribute, value) triples, which will be used as the pretraining corpus. To more effectively utilize the retrieved corpus, we further design a Knowledge-Selective Framework (KSelF) based on query expansion that can be closely combined with the pretraining corpus to boost the performance. Meanwhile, considering the public AE-pub dataset contains considerable noise, we construct and contribute a larger benchmark EC-AVE collected from E-commerce websites. We conduct evaluation on both of these datasets. The experimental results demonstrate that our proposed KSelF achieves new state-of-the-art performance without pretraining. When incorporated with the pretraining corpus, the performance of KSelF can be further improved, particularly on the attributes with limited training resources.
%R 10.18653/v1/2023.findings-emnlp.542
%U https://aclanthology.org/2023.findings-emnlp.542
%U https://doi.org/10.18653/v1/2023.findings-emnlp.542
%P 8062-8074
Markdown (Informal)
[Knowledge-Selective Pretraining for Attribute Value Extraction](https://aclanthology.org/2023.findings-emnlp.542) (Liu et al., Findings 2023)
ACL
- Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chao Zhang, Bing Yin, William Wang, and Xiaodan Zhu. 2023. Knowledge-Selective Pretraining for Attribute Value Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8062–8074, Singapore. Association for Computational Linguistics.