@inproceedings{shinzato-etal-2022-simple,
title = "Simple and Effective Knowledge-Driven Query Expansion for {QA}-Based Product Attribute Extraction",
author = "Shinzato, Keiji and
Yoshinaga, Naoki and
Xia, Yandi and
Chen, Wei-Te",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-short.25",
doi = "10.18653/v1/2022.acl-short.25",
pages = "227--234",
abstract = "A key challenge in attribute value extraction (AVE) from e-commerce sites is how to handle a large number of attributes for diverse products. Although this challenge is partially addressed by a question answering (QA) approach which finds a value in product data for a given query (attribute), it does not work effectively for rare and ambiguous queries. We thus propose simple knowledge-driven query expansion based on possible answers (values) of a query (attribute) for QA-based AVE. We retrieve values of a query (attribute) from the training data to expand the query. We train a model with two tricks, knowledge dropout and knowledge token mixing, which mimic the imperfection of the value knowledge in testing. Experimental results on our cleaned version of AliExpress dataset show that our method improves the performance of AVE (+6.08 macro F1), especially for rare and ambiguous attributes (+7.82 and +6.86 macro F1, respectively).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shinzato-etal-2022-simple">
<titleInfo>
<title>Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keiji</namePart>
<namePart type="family">Shinzato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Yoshinaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yandi</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Te</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A key challenge in attribute value extraction (AVE) from e-commerce sites is how to handle a large number of attributes for diverse products. Although this challenge is partially addressed by a question answering (QA) approach which finds a value in product data for a given query (attribute), it does not work effectively for rare and ambiguous queries. We thus propose simple knowledge-driven query expansion based on possible answers (values) of a query (attribute) for QA-based AVE. We retrieve values of a query (attribute) from the training data to expand the query. We train a model with two tricks, knowledge dropout and knowledge token mixing, which mimic the imperfection of the value knowledge in testing. Experimental results on our cleaned version of AliExpress dataset show that our method improves the performance of AVE (+6.08 macro F1), especially for rare and ambiguous attributes (+7.82 and +6.86 macro F1, respectively).</abstract>
<identifier type="citekey">shinzato-etal-2022-simple</identifier>
<identifier type="doi">10.18653/v1/2022.acl-short.25</identifier>
<location>
<url>https://aclanthology.org/2022.acl-short.25</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>227</start>
<end>234</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute Extraction
%A Shinzato, Keiji
%A Yoshinaga, Naoki
%A Xia, Yandi
%A Chen, Wei-Te
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F shinzato-etal-2022-simple
%X A key challenge in attribute value extraction (AVE) from e-commerce sites is how to handle a large number of attributes for diverse products. Although this challenge is partially addressed by a question answering (QA) approach which finds a value in product data for a given query (attribute), it does not work effectively for rare and ambiguous queries. We thus propose simple knowledge-driven query expansion based on possible answers (values) of a query (attribute) for QA-based AVE. We retrieve values of a query (attribute) from the training data to expand the query. We train a model with two tricks, knowledge dropout and knowledge token mixing, which mimic the imperfection of the value knowledge in testing. Experimental results on our cleaned version of AliExpress dataset show that our method improves the performance of AVE (+6.08 macro F1), especially for rare and ambiguous attributes (+7.82 and +6.86 macro F1, respectively).
%R 10.18653/v1/2022.acl-short.25
%U https://aclanthology.org/2022.acl-short.25
%U https://doi.org/10.18653/v1/2022.acl-short.25
%P 227-234
Markdown (Informal)
[Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute Extraction](https://aclanthology.org/2022.acl-short.25) (Shinzato et al., ACL 2022)
ACL