@inproceedings{xia-etal-2017-large,
title = "Large-Scale Categorization of {J}apanese Product Titles Using Neural Attention Models",
author = "Xia, Yandi and
Levine, Aaron and
Das, Pradipto and
Di Fabbrizio, Giuseppe and
Shinzato, Keiji and
Datta, Ankur",
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 2, Short Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-2105",
pages = "663--668",
abstract = "We propose a variant of Convolutional Neural Network (CNN) models, the Attention CNN (ACNN); for large-scale categorization of millions of Japanese items into thirty-five product categories. Compared to a state-of-the-art Gradient Boosted Tree (GBT) classifier, the proposed model reduces training time from three weeks to three days while maintaining more than 96{\%} accuracy. Additionally, our proposed model characterizes products by imputing attentive focus on word tokens in a language agnostic way. The attention words have been observed to be semantically highly correlated with the predicted categories and give us a choice of automatic feature extraction for downstream processing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xia-etal-2017-large">
<titleInfo>
<title>Large-Scale Categorization of Japanese Product Titles Using Neural Attention Models</title>
</titleInfo>
<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">Aaron</namePart>
<namePart type="family">Levine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pradipto</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Di Fabbrizio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Ankur</namePart>
<namePart type="family">Datta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a variant of Convolutional Neural Network (CNN) models, the Attention CNN (ACNN); for large-scale categorization of millions of Japanese items into thirty-five product categories. Compared to a state-of-the-art Gradient Boosted Tree (GBT) classifier, the proposed model reduces training time from three weeks to three days while maintaining more than 96% accuracy. Additionally, our proposed model characterizes products by imputing attentive focus on word tokens in a language agnostic way. The attention words have been observed to be semantically highly correlated with the predicted categories and give us a choice of automatic feature extraction for downstream processing.</abstract>
<identifier type="citekey">xia-etal-2017-large</identifier>
<location>
<url>https://aclanthology.org/E17-2105</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>663</start>
<end>668</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large-Scale Categorization of Japanese Product Titles Using Neural Attention Models
%A Xia, Yandi
%A Levine, Aaron
%A Das, Pradipto
%A Di Fabbrizio, Giuseppe
%A Shinzato, Keiji
%A Datta, Ankur
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F xia-etal-2017-large
%X We propose a variant of Convolutional Neural Network (CNN) models, the Attention CNN (ACNN); for large-scale categorization of millions of Japanese items into thirty-five product categories. Compared to a state-of-the-art Gradient Boosted Tree (GBT) classifier, the proposed model reduces training time from three weeks to three days while maintaining more than 96% accuracy. Additionally, our proposed model characterizes products by imputing attentive focus on word tokens in a language agnostic way. The attention words have been observed to be semantically highly correlated with the predicted categories and give us a choice of automatic feature extraction for downstream processing.
%U https://aclanthology.org/E17-2105
%P 663-668
Markdown (Informal)
[Large-Scale Categorization of Japanese Product Titles Using Neural Attention Models](https://aclanthology.org/E17-2105) (Xia et al., EACL 2017)
ACL