@inproceedings{xu-etal-2021-hierarchical,
title = "Hierarchical Multi-label Text Classification with Horizontal and Vertical Category Correlations",
author = "Xu, Linli and
Teng, Sijie and
Zhao, Ruoyu and
Guo, Junliang and
Xiao, Chi and
Jiang, Deqiang and
Ren, Bo",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.190",
doi = "10.18653/v1/2021.emnlp-main.190",
pages = "2459--2468",
abstract = "Hierarchical multi-label text classification (HMTC) deals with the challenging task where an instance can be assigned to multiple hierarchically structured categories at the same time. The majority of prior studies either focus on reducing the HMTC task into a flat multi-label problem ignoring the vertical category correlations or exploiting the dependencies across different hierarchical levels without considering the horizontal correlations among categories at the same level, which inevitably leads to fundamental information loss. In this paper, we propose a novel HMTC framework that considers both vertical and horizontal category correlations. Specifically, we first design a loosely coupled graph convolutional neural network as the representation extractor to obtain representations for words, documents, and, more importantly, level-wise representations for categories, which are not considered in previous works. Then, the learned category representations are adopted to capture the vertical dependencies among levels of category hierarchy and model the horizontal correlations. Finally, based on the document embeddings and category embeddings, we design a hybrid algorithm to predict the categories of the entire hierarchical structure. Extensive experiments conducted on real-world HMTC datasets validate the effectiveness of the proposed framework with significant improvements over the baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2021-hierarchical">
<titleInfo>
<title>Hierarchical Multi-label Text Classification with Horizontal and Vertical Category Correlations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Linli</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sijie</namePart>
<namePart type="family">Teng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruoyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junliang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chi</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deqiang</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hierarchical multi-label text classification (HMTC) deals with the challenging task where an instance can be assigned to multiple hierarchically structured categories at the same time. The majority of prior studies either focus on reducing the HMTC task into a flat multi-label problem ignoring the vertical category correlations or exploiting the dependencies across different hierarchical levels without considering the horizontal correlations among categories at the same level, which inevitably leads to fundamental information loss. In this paper, we propose a novel HMTC framework that considers both vertical and horizontal category correlations. Specifically, we first design a loosely coupled graph convolutional neural network as the representation extractor to obtain representations for words, documents, and, more importantly, level-wise representations for categories, which are not considered in previous works. Then, the learned category representations are adopted to capture the vertical dependencies among levels of category hierarchy and model the horizontal correlations. Finally, based on the document embeddings and category embeddings, we design a hybrid algorithm to predict the categories of the entire hierarchical structure. Extensive experiments conducted on real-world HMTC datasets validate the effectiveness of the proposed framework with significant improvements over the baselines.</abstract>
<identifier type="citekey">xu-etal-2021-hierarchical</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.190</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.190</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2459</start>
<end>2468</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hierarchical Multi-label Text Classification with Horizontal and Vertical Category Correlations
%A Xu, Linli
%A Teng, Sijie
%A Zhao, Ruoyu
%A Guo, Junliang
%A Xiao, Chi
%A Jiang, Deqiang
%A Ren, Bo
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F xu-etal-2021-hierarchical
%X Hierarchical multi-label text classification (HMTC) deals with the challenging task where an instance can be assigned to multiple hierarchically structured categories at the same time. The majority of prior studies either focus on reducing the HMTC task into a flat multi-label problem ignoring the vertical category correlations or exploiting the dependencies across different hierarchical levels without considering the horizontal correlations among categories at the same level, which inevitably leads to fundamental information loss. In this paper, we propose a novel HMTC framework that considers both vertical and horizontal category correlations. Specifically, we first design a loosely coupled graph convolutional neural network as the representation extractor to obtain representations for words, documents, and, more importantly, level-wise representations for categories, which are not considered in previous works. Then, the learned category representations are adopted to capture the vertical dependencies among levels of category hierarchy and model the horizontal correlations. Finally, based on the document embeddings and category embeddings, we design a hybrid algorithm to predict the categories of the entire hierarchical structure. Extensive experiments conducted on real-world HMTC datasets validate the effectiveness of the proposed framework with significant improvements over the baselines.
%R 10.18653/v1/2021.emnlp-main.190
%U https://aclanthology.org/2021.emnlp-main.190
%U https://doi.org/10.18653/v1/2021.emnlp-main.190
%P 2459-2468
Markdown (Informal)
[Hierarchical Multi-label Text Classification with Horizontal and Vertical Category Correlations](https://aclanthology.org/2021.emnlp-main.190) (Xu et al., EMNLP 2021)
ACL