@inproceedings{shen-etal-2021-taxoclass,
title = "{T}axo{C}lass: Hierarchical Multi-Label Text Classification Using Only Class Names",
author = "Shen, Jiaming and
Qiu, Wenda and
Meng, Yu and
Shang, Jingbo and
Ren, Xiang and
Han, Jiawei",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.335",
doi = "10.18653/v1/2021.naacl-main.335",
pages = "4239--4249",
abstract = "Hierarchical multi-label text classification (HMTC) aims to tag each document with a set of classes from a taxonomic class hierarchy. Most existing HMTC methods train classifiers using massive human-labeled documents, which are often too costly to obtain in real-world applications. In this paper, we explore to conduct HMTC based on only class surface names as supervision signals. We observe that to perform HMTC, human experts typically first pinpoint a few most essential classes for the document as its {``}core classes{''}, and then check core classes{'} ancestor classes to ensure the coverage. To mimic human experts, we propose a novel HMTC framework, named TaxoClass. Specifically, TaxoClass (1) calculates document-class similarities using a textual entailment model, (2) identifies a document{'}s core classes and utilizes confident core classes to train a taxonomy-enhanced classifier, and (3) generalizes the classifier via multi-label self-training. Our experiments on two challenging datasets show TaxoClass can achieve around 0.71 Example-F1 using only class names, outperforming the best previous method by 25{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2021-taxoclass">
<titleInfo>
<title>TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class Names</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaming</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenda</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingbo</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Han</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 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hierarchical multi-label text classification (HMTC) aims to tag each document with a set of classes from a taxonomic class hierarchy. Most existing HMTC methods train classifiers using massive human-labeled documents, which are often too costly to obtain in real-world applications. In this paper, we explore to conduct HMTC based on only class surface names as supervision signals. We observe that to perform HMTC, human experts typically first pinpoint a few most essential classes for the document as its “core classes”, and then check core classes’ ancestor classes to ensure the coverage. To mimic human experts, we propose a novel HMTC framework, named TaxoClass. Specifically, TaxoClass (1) calculates document-class similarities using a textual entailment model, (2) identifies a document’s core classes and utilizes confident core classes to train a taxonomy-enhanced classifier, and (3) generalizes the classifier via multi-label self-training. Our experiments on two challenging datasets show TaxoClass can achieve around 0.71 Example-F1 using only class names, outperforming the best previous method by 25%.</abstract>
<identifier type="citekey">shen-etal-2021-taxoclass</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.335</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.335</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>4239</start>
<end>4249</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class Names
%A Shen, Jiaming
%A Qiu, Wenda
%A Meng, Yu
%A Shang, Jingbo
%A Ren, Xiang
%A Han, Jiawei
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F shen-etal-2021-taxoclass
%X Hierarchical multi-label text classification (HMTC) aims to tag each document with a set of classes from a taxonomic class hierarchy. Most existing HMTC methods train classifiers using massive human-labeled documents, which are often too costly to obtain in real-world applications. In this paper, we explore to conduct HMTC based on only class surface names as supervision signals. We observe that to perform HMTC, human experts typically first pinpoint a few most essential classes for the document as its “core classes”, and then check core classes’ ancestor classes to ensure the coverage. To mimic human experts, we propose a novel HMTC framework, named TaxoClass. Specifically, TaxoClass (1) calculates document-class similarities using a textual entailment model, (2) identifies a document’s core classes and utilizes confident core classes to train a taxonomy-enhanced classifier, and (3) generalizes the classifier via multi-label self-training. Our experiments on two challenging datasets show TaxoClass can achieve around 0.71 Example-F1 using only class names, outperforming the best previous method by 25%.
%R 10.18653/v1/2021.naacl-main.335
%U https://aclanthology.org/2021.naacl-main.335
%U https://doi.org/10.18653/v1/2021.naacl-main.335
%P 4239-4249
Markdown (Informal)
[TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class Names](https://aclanthology.org/2021.naacl-main.335) (Shen et al., NAACL 2021)
ACL