@inproceedings{jin-etal-2017-combining,
title = "Combining Lightly-Supervised Text Classification Models for Accurate Contextual Advertising",
author = "Jin, Yiping and
Wanvarie, Dittaya and
Le, Phu",
editor = "Kondrak, Greg and
Watanabe, Taro",
booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = nov,
year = "2017",
address = "Taipei, Taiwan",
publisher = "Asian Federation of Natural Language Processing",
url = "https://aclanthology.org/I17-1055",
pages = "545--554",
abstract = "In this paper we propose a lightly-supervised framework to rapidly build text classifiers for contextual advertising. Traditionally text classification techniques require labeled training documents for each predefined class. In the scenario of contextual advertising, advertisers often want to target to a specific class of webpages most relevant to their product or service, which may not be covered by a pre-trained classifier. Moreover, the advertisers are interested in whether a webpage is {``}relevant{''} or {``}irrelevant{''}. It is time-consuming to solicit the advertisers for reliable training signals for the negative class. Therefore, it is more suitable to model the problem as a one-class classification problem, in contrast to traditional classification problems where disjoint classes are defined a priori. We first apply two state-of-the-art lightly-supervised classification models, generalized expectation (GE) criteria (Druck et al., 2008) and multinomial naive Bayes (MNB) with priors (Settles, 2011) to one-class classification where the user only needs to provide a small list of labeled words for the target class. To combine the strengths of the two models, we fuse them together by using MNB to automatically enrich the constraints for GE training. We also explore ensemble method to combine classifiers. On a corpus of webpages from real-time bidding requests, the proposed model achieves the highest average F1 of 0.69 and closes more than half of the gap between previous state-of-the-art lightly-supervised models to a fully-supervised MaxEnt model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2017-combining">
<titleInfo>
<title>Combining Lightly-Supervised Text Classification Models for Accurate Contextual Advertising</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiping</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dittaya</namePart>
<namePart type="family">Wanvarie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phu</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Kondrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asian Federation of Natural Language Processing</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we propose a lightly-supervised framework to rapidly build text classifiers for contextual advertising. Traditionally text classification techniques require labeled training documents for each predefined class. In the scenario of contextual advertising, advertisers often want to target to a specific class of webpages most relevant to their product or service, which may not be covered by a pre-trained classifier. Moreover, the advertisers are interested in whether a webpage is “relevant” or “irrelevant”. It is time-consuming to solicit the advertisers for reliable training signals for the negative class. Therefore, it is more suitable to model the problem as a one-class classification problem, in contrast to traditional classification problems where disjoint classes are defined a priori. We first apply two state-of-the-art lightly-supervised classification models, generalized expectation (GE) criteria (Druck et al., 2008) and multinomial naive Bayes (MNB) with priors (Settles, 2011) to one-class classification where the user only needs to provide a small list of labeled words for the target class. To combine the strengths of the two models, we fuse them together by using MNB to automatically enrich the constraints for GE training. We also explore ensemble method to combine classifiers. On a corpus of webpages from real-time bidding requests, the proposed model achieves the highest average F1 of 0.69 and closes more than half of the gap between previous state-of-the-art lightly-supervised models to a fully-supervised MaxEnt model.</abstract>
<identifier type="citekey">jin-etal-2017-combining</identifier>
<location>
<url>https://aclanthology.org/I17-1055</url>
</location>
<part>
<date>2017-11</date>
<extent unit="page">
<start>545</start>
<end>554</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Combining Lightly-Supervised Text Classification Models for Accurate Contextual Advertising
%A Jin, Yiping
%A Wanvarie, Dittaya
%A Le, Phu
%Y Kondrak, Greg
%Y Watanabe, Taro
%S Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2017
%8 November
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F jin-etal-2017-combining
%X In this paper we propose a lightly-supervised framework to rapidly build text classifiers for contextual advertising. Traditionally text classification techniques require labeled training documents for each predefined class. In the scenario of contextual advertising, advertisers often want to target to a specific class of webpages most relevant to their product or service, which may not be covered by a pre-trained classifier. Moreover, the advertisers are interested in whether a webpage is “relevant” or “irrelevant”. It is time-consuming to solicit the advertisers for reliable training signals for the negative class. Therefore, it is more suitable to model the problem as a one-class classification problem, in contrast to traditional classification problems where disjoint classes are defined a priori. We first apply two state-of-the-art lightly-supervised classification models, generalized expectation (GE) criteria (Druck et al., 2008) and multinomial naive Bayes (MNB) with priors (Settles, 2011) to one-class classification where the user only needs to provide a small list of labeled words for the target class. To combine the strengths of the two models, we fuse them together by using MNB to automatically enrich the constraints for GE training. We also explore ensemble method to combine classifiers. On a corpus of webpages from real-time bidding requests, the proposed model achieves the highest average F1 of 0.69 and closes more than half of the gap between previous state-of-the-art lightly-supervised models to a fully-supervised MaxEnt model.
%U https://aclanthology.org/I17-1055
%P 545-554
Markdown (Informal)
[Combining Lightly-Supervised Text Classification Models for Accurate Contextual Advertising](https://aclanthology.org/I17-1055) (Jin et al., IJCNLP 2017)
ACL