@inproceedings{zhang-zhang-2020-text,
title = "Text Graph Transformer for Document Classification",
author = "Zhang, Haopeng and
Zhang, Jiawei",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.668/",
doi = "10.18653/v1/2020.emnlp-main.668",
pages = "8322--8327",
abstract = "Text classification is a fundamental problem in natural language processing. Recent studies applied graph neural network (GNN) techniques to capture global word co-occurrence in a corpus. However, previous works are not scalable to large-sized corpus and ignore the heterogeneity of the text graph. To address these problems, we introduce a novel Transformer based heterogeneous graph neural network, namely Text Graph Transformer (TG-Transformer). Our model learns effective node representations by capturing structure and heterogeneity from the text graph. We propose a mini-batch text graph sampling method that significantly reduces computing and memory costs to handle large-sized corpus. Extensive experiments have been conducted on several benchmark datasets, and the results demonstrate that TG-Transformer outperforms state-of-the-art approaches on text classification task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-zhang-2020-text">
<titleInfo>
<title>Text Graph Transformer for Document Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haopeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Text classification is a fundamental problem in natural language processing. Recent studies applied graph neural network (GNN) techniques to capture global word co-occurrence in a corpus. However, previous works are not scalable to large-sized corpus and ignore the heterogeneity of the text graph. To address these problems, we introduce a novel Transformer based heterogeneous graph neural network, namely Text Graph Transformer (TG-Transformer). Our model learns effective node representations by capturing structure and heterogeneity from the text graph. We propose a mini-batch text graph sampling method that significantly reduces computing and memory costs to handle large-sized corpus. Extensive experiments have been conducted on several benchmark datasets, and the results demonstrate that TG-Transformer outperforms state-of-the-art approaches on text classification task.</abstract>
<identifier type="citekey">zhang-zhang-2020-text</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.668</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.668/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>8322</start>
<end>8327</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text Graph Transformer for Document Classification
%A Zhang, Haopeng
%A Zhang, Jiawei
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F zhang-zhang-2020-text
%X Text classification is a fundamental problem in natural language processing. Recent studies applied graph neural network (GNN) techniques to capture global word co-occurrence in a corpus. However, previous works are not scalable to large-sized corpus and ignore the heterogeneity of the text graph. To address these problems, we introduce a novel Transformer based heterogeneous graph neural network, namely Text Graph Transformer (TG-Transformer). Our model learns effective node representations by capturing structure and heterogeneity from the text graph. We propose a mini-batch text graph sampling method that significantly reduces computing and memory costs to handle large-sized corpus. Extensive experiments have been conducted on several benchmark datasets, and the results demonstrate that TG-Transformer outperforms state-of-the-art approaches on text classification task.
%R 10.18653/v1/2020.emnlp-main.668
%U https://aclanthology.org/2020.emnlp-main.668/
%U https://doi.org/10.18653/v1/2020.emnlp-main.668
%P 8322-8327
Markdown (Informal)
[Text Graph Transformer for Document Classification](https://aclanthology.org/2020.emnlp-main.668/) (Zhang & Zhang, EMNLP 2020)
ACL
- Haopeng Zhang and Jiawei Zhang. 2020. Text Graph Transformer for Document Classification. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8322–8327, Online. Association for Computational Linguistics.