@inproceedings{liu-etal-2018-semi,
title = "Semi-Supervised Learning with Auxiliary Evaluation Component for Large Scale e-Commerce Text Classification",
author = "Liu, Mingkuan and
Wen, Musen and
Kopru, Selcuk and
Liu, Xianjing and
Lu, Alan",
editor = "Haffari, Reza and
Cherry, Colin and
Foster, George and
Khadivi, Shahram and
Salehi, Bahar",
booktitle = "Proceedings of the Workshop on Deep Learning Approaches for Low-Resource {NLP}",
month = jul,
year = "2018",
address = "Melbourne",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3409",
doi = "10.18653/v1/W18-3409",
pages = "68--76",
abstract = "The lack of high-quality labeled training data has been one of the critical challenges facing many industrial machine learning tasks. To tackle this challenge, in this paper, we propose a semi-supervised learning method to utilize unlabeled data and user feedback signals to improve the performance of ML models. The method employs a primary model Main and an auxiliary evaluation model Eval, where Main and Eval models are trained iteratively by automatically generating labeled data from unlabeled data and/or users{'} feedback signals. The proposed approach is applied to different text classification tasks. We report results on both the publicly available Yahoo! Answers dataset and our e-commerce product classification dataset. The experimental results show that the proposed method reduces the classification error rate by 4{\%} and up to 15{\%} across various experimental setups and datasets. A detailed comparison with other semi-supervised learning approaches is also presented later in the paper. The results from various text classification tasks demonstrate that our method outperforms those developed in previous related studies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2018-semi">
<titleInfo>
<title>Semi-Supervised Learning with Auxiliary Evaluation Component for Large Scale e-Commerce Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingkuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Musen</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Selcuk</namePart>
<namePart type="family">Kopru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianjing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bahar</namePart>
<namePart type="family">Salehi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The lack of high-quality labeled training data has been one of the critical challenges facing many industrial machine learning tasks. To tackle this challenge, in this paper, we propose a semi-supervised learning method to utilize unlabeled data and user feedback signals to improve the performance of ML models. The method employs a primary model Main and an auxiliary evaluation model Eval, where Main and Eval models are trained iteratively by automatically generating labeled data from unlabeled data and/or users’ feedback signals. The proposed approach is applied to different text classification tasks. We report results on both the publicly available Yahoo! Answers dataset and our e-commerce product classification dataset. The experimental results show that the proposed method reduces the classification error rate by 4% and up to 15% across various experimental setups and datasets. A detailed comparison with other semi-supervised learning approaches is also presented later in the paper. The results from various text classification tasks demonstrate that our method outperforms those developed in previous related studies.</abstract>
<identifier type="citekey">liu-etal-2018-semi</identifier>
<identifier type="doi">10.18653/v1/W18-3409</identifier>
<location>
<url>https://aclanthology.org/W18-3409</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>68</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-Supervised Learning with Auxiliary Evaluation Component for Large Scale e-Commerce Text Classification
%A Liu, Mingkuan
%A Wen, Musen
%A Kopru, Selcuk
%A Liu, Xianjing
%A Lu, Alan
%Y Haffari, Reza
%Y Cherry, Colin
%Y Foster, George
%Y Khadivi, Shahram
%Y Salehi, Bahar
%S Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne
%F liu-etal-2018-semi
%X The lack of high-quality labeled training data has been one of the critical challenges facing many industrial machine learning tasks. To tackle this challenge, in this paper, we propose a semi-supervised learning method to utilize unlabeled data and user feedback signals to improve the performance of ML models. The method employs a primary model Main and an auxiliary evaluation model Eval, where Main and Eval models are trained iteratively by automatically generating labeled data from unlabeled data and/or users’ feedback signals. The proposed approach is applied to different text classification tasks. We report results on both the publicly available Yahoo! Answers dataset and our e-commerce product classification dataset. The experimental results show that the proposed method reduces the classification error rate by 4% and up to 15% across various experimental setups and datasets. A detailed comparison with other semi-supervised learning approaches is also presented later in the paper. The results from various text classification tasks demonstrate that our method outperforms those developed in previous related studies.
%R 10.18653/v1/W18-3409
%U https://aclanthology.org/W18-3409
%U https://doi.org/10.18653/v1/W18-3409
%P 68-76
Markdown (Informal)
[Semi-Supervised Learning with Auxiliary Evaluation Component for Large Scale e-Commerce Text Classification](https://aclanthology.org/W18-3409) (Liu et al., ACL 2018)
ACL