@inproceedings{tayal-etal-2020-regularized,
title = "Regularized Graph Convolutional Networks for Short Text Classification",
author = "Tayal, Kshitij and
Rao, Nikhil and
Agarwal, Saurabh and
Jia, Xiaowei and
Subbian, Karthik and
Kumar, Vipin",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics: Industry Track",
month = dec,
year = "2020",
address = "Online",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-industry.22",
doi = "10.18653/v1/2020.coling-industry.22",
pages = "236--242",
abstract = "Short text classification is a fundamental problem in natural language processing, social network analysis, and e-commerce. The lack of structure in short text sequences limits the success of popular NLP methods based on deep learning. Simpler methods that rely on bag-of-words representations tend to perform on par with complex deep learning methods. To tackle the limitations of textual features in short text, we propose a Graph-regularized Graph Convolution Network (GR-GCN), which augments graph convolution networks by incorporating label dependencies in the output space. Our model achieves state-of-the-art results on both proprietary and external datasets, outperforming several baseline methods by up to 6{\%} . Furthermore, we show that compared to baseline methods, GR-GCN is more robust to noise in textual features.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tayal-etal-2020-regularized">
<titleInfo>
<title>Regularized Graph Convolutional Networks for Short Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kshitij</namePart>
<namePart type="family">Tayal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saurabh</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaowei</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="family">Subbian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vipin</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Short text classification is a fundamental problem in natural language processing, social network analysis, and e-commerce. The lack of structure in short text sequences limits the success of popular NLP methods based on deep learning. Simpler methods that rely on bag-of-words representations tend to perform on par with complex deep learning methods. To tackle the limitations of textual features in short text, we propose a Graph-regularized Graph Convolution Network (GR-GCN), which augments graph convolution networks by incorporating label dependencies in the output space. Our model achieves state-of-the-art results on both proprietary and external datasets, outperforming several baseline methods by up to 6% . Furthermore, we show that compared to baseline methods, GR-GCN is more robust to noise in textual features.</abstract>
<identifier type="citekey">tayal-etal-2020-regularized</identifier>
<identifier type="doi">10.18653/v1/2020.coling-industry.22</identifier>
<location>
<url>https://aclanthology.org/2020.coling-industry.22</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>236</start>
<end>242</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Regularized Graph Convolutional Networks for Short Text Classification
%A Tayal, Kshitij
%A Rao, Nikhil
%A Agarwal, Saurabh
%A Jia, Xiaowei
%A Subbian, Karthik
%A Kumar, Vipin
%S Proceedings of the 28th International Conference on Computational Linguistics: Industry Track
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Online
%F tayal-etal-2020-regularized
%X Short text classification is a fundamental problem in natural language processing, social network analysis, and e-commerce. The lack of structure in short text sequences limits the success of popular NLP methods based on deep learning. Simpler methods that rely on bag-of-words representations tend to perform on par with complex deep learning methods. To tackle the limitations of textual features in short text, we propose a Graph-regularized Graph Convolution Network (GR-GCN), which augments graph convolution networks by incorporating label dependencies in the output space. Our model achieves state-of-the-art results on both proprietary and external datasets, outperforming several baseline methods by up to 6% . Furthermore, we show that compared to baseline methods, GR-GCN is more robust to noise in textual features.
%R 10.18653/v1/2020.coling-industry.22
%U https://aclanthology.org/2020.coling-industry.22
%U https://doi.org/10.18653/v1/2020.coling-industry.22
%P 236-242
Markdown (Informal)
[Regularized Graph Convolutional Networks for Short Text Classification](https://aclanthology.org/2020.coling-industry.22) (Tayal et al., COLING 2020)
ACL