@inproceedings{jin-etal-2021-bootstrapping,
title = "Bootstrapping Large-Scale Fine-Grained Contextual Advertising Classifier from {W}ikipedia",
author = "Jin, Yiping and
Kadam, Vishakha and
Wanvarie, Dittaya",
editor = "Panchenko, Alexander and
Malliaros, Fragkiskos D. and
Logacheva, Varvara and
Jana, Abhik and
Ustalov, Dmitry and
Jansen, Peter",
booktitle = "Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)",
month = jun,
year = "2021",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.textgraphs-1.1",
doi = "10.18653/v1/2021.textgraphs-1.1",
pages = "1--9",
abstract = "Contextual advertising provides advertisers with the opportunity to target the context which is most relevant to their ads. The large variety of potential topics makes it very challenging to collect training documents to build a supervised classification model or compose expert-written rules in a rule-based classification system. Besides, in fine-grained classification, different categories often overlap or co-occur, making it harder to classify accurately. In this work, we propose wiki2cat, a method to tackle large-scaled fine-grained text classification by tapping on the Wikipedia category graph. The categories in the IAB taxonomy are first mapped to category nodes in the graph. Then the label is propagated across the graph to obtain a list of labeled Wikipedia documents to induce text classifiers. The method is ideal for large-scale classification problems since it does not require any manually-labeled document or hand-curated rules or keywords. The proposed method is benchmarked with various learning-based and keyword-based baselines and yields competitive performance on publicly available datasets and a new dataset containing more than 300 fine-grained categories.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2021-bootstrapping">
<titleInfo>
<title>Bootstrapping Large-Scale Fine-Grained Contextual Advertising Classifier from Wikipedia</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">Vishakha</namePart>
<namePart type="family">Kadam</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>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fragkiskos</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Malliaros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhik</namePart>
<namePart type="family">Jana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Ustalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Jansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Contextual advertising provides advertisers with the opportunity to target the context which is most relevant to their ads. The large variety of potential topics makes it very challenging to collect training documents to build a supervised classification model or compose expert-written rules in a rule-based classification system. Besides, in fine-grained classification, different categories often overlap or co-occur, making it harder to classify accurately. In this work, we propose wiki2cat, a method to tackle large-scaled fine-grained text classification by tapping on the Wikipedia category graph. The categories in the IAB taxonomy are first mapped to category nodes in the graph. Then the label is propagated across the graph to obtain a list of labeled Wikipedia documents to induce text classifiers. The method is ideal for large-scale classification problems since it does not require any manually-labeled document or hand-curated rules or keywords. The proposed method is benchmarked with various learning-based and keyword-based baselines and yields competitive performance on publicly available datasets and a new dataset containing more than 300 fine-grained categories.</abstract>
<identifier type="citekey">jin-etal-2021-bootstrapping</identifier>
<identifier type="doi">10.18653/v1/2021.textgraphs-1.1</identifier>
<location>
<url>https://aclanthology.org/2021.textgraphs-1.1</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>1</start>
<end>9</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bootstrapping Large-Scale Fine-Grained Contextual Advertising Classifier from Wikipedia
%A Jin, Yiping
%A Kadam, Vishakha
%A Wanvarie, Dittaya
%Y Panchenko, Alexander
%Y Malliaros, Fragkiskos D.
%Y Logacheva, Varvara
%Y Jana, Abhik
%Y Ustalov, Dmitry
%Y Jansen, Peter
%S Proceedings of the Fifteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-15)
%D 2021
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F jin-etal-2021-bootstrapping
%X Contextual advertising provides advertisers with the opportunity to target the context which is most relevant to their ads. The large variety of potential topics makes it very challenging to collect training documents to build a supervised classification model or compose expert-written rules in a rule-based classification system. Besides, in fine-grained classification, different categories often overlap or co-occur, making it harder to classify accurately. In this work, we propose wiki2cat, a method to tackle large-scaled fine-grained text classification by tapping on the Wikipedia category graph. The categories in the IAB taxonomy are first mapped to category nodes in the graph. Then the label is propagated across the graph to obtain a list of labeled Wikipedia documents to induce text classifiers. The method is ideal for large-scale classification problems since it does not require any manually-labeled document or hand-curated rules or keywords. The proposed method is benchmarked with various learning-based and keyword-based baselines and yields competitive performance on publicly available datasets and a new dataset containing more than 300 fine-grained categories.
%R 10.18653/v1/2021.textgraphs-1.1
%U https://aclanthology.org/2021.textgraphs-1.1
%U https://doi.org/10.18653/v1/2021.textgraphs-1.1
%P 1-9
Markdown (Informal)
[Bootstrapping Large-Scale Fine-Grained Contextual Advertising Classifier from Wikipedia](https://aclanthology.org/2021.textgraphs-1.1) (Jin et al., TextGraphs 2021)
ACL