Multi-Label Classification of Chinese Humor Texts Using Hypergraph Attention Networks

Hao Chuan Kao; Man Chen Hung; Lung Hao Lee; Yuen Hsien Tseng

Multi-Label Classification of Chinese Humor Texts Using Hypergraph Attention Networks

Hao Chuan Kao, Man Chen Hung, Lung Hao Lee, Yuen Hsien Tseng

電機工程學系

研究成果: 書貢獻/報告類型 › 會議論文篇章 › 同行評審

1 引文斯高帕斯（Scopus）

摘要

We use Hypergraph Attention Networks (HyperGAT) to recognize multiple labels of Chinese humor texts. We firstly represent a joke as a hypergraph. The sequential hyperedge and semantic hyperedge structures are used to construct hyperedges. Then, attention mechanisms are adopted to aggregate context information embedded in nodes and hyperedges. Finally we use trained HyperGAT to complete the multi-label classification task. Experimental results on the Chinese humor multi-label dataset showed that HyperGAT model outperforms previous sequence-based (CNN, BiLSTM, FastText) and graph-based (Graph-CNN, TextGCN, Text Level GNN) deep learning models.

原文	???core.languages.en_GB???
主出版物標題	ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing
編輯	Lung-Hao Lee, Chia-Hui Chang, Kuan-Yu Chen
發行者	The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
頁面	257-264
頁數	8
ISBN（電子）	9789869576949
出版狀態	已出版 - 2021
事件	33rd Conference on Computational Linguistics and Speech Processing, ROCLING 2021 - Taoyuan, Taiwan 持續時間: 15 10月 2021 → 16 10月 2021

出版系列

名字	ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	33rd Conference on Computational Linguistics and Speech Processing, ROCLING 2021
國家/地區	Taiwan
城市	Taoyuan
期間	15/10/21 → 16/10/21

中文醫療健康照護知識庫建置與應用(2/3)
Lee, L.-H. (PI)
1/05/20 → 30/04/21
研究計畫: Research

引用此

Kao, H. C., Hung, M. C., Lee, L. H., & Tseng, Y. H. (2021). Multi-Label Classification of Chinese Humor Texts Using Hypergraph Attention Networks. 於 L.-H. Lee, C.-H. Chang, & K.-Y. Chen (編輯), ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (頁 257-264). (ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing). The Association for Computational Linguistics and Chinese Language Processing (ACLCLP).

Kao, Hao Chuan ; Hung, Man Chen ; Lee, Lung Hao 等. / Multi-Label Classification of Chinese Humor Texts Using Hypergraph Attention Networks. ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing. 編輯 / Lung-Hao Lee ; Chia-Hui Chang ; Kuan-Yu Chen. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP), 2021. 頁 257-264 (ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing).

@inproceedings{2cc7f8ab4ff04e4995fede59034a7560,

title = "Multi-Label Classification of Chinese Humor Texts Using Hypergraph Attention Networks",

abstract = "We use Hypergraph Attention Networks (HyperGAT) to recognize multiple labels of Chinese humor texts. We firstly represent a joke as a hypergraph. The sequential hyperedge and semantic hyperedge structures are used to construct hyperedges. Then, attention mechanisms are adopted to aggregate context information embedded in nodes and hyperedges. Finally we use trained HyperGAT to complete the multi-label classification task. Experimental results on the Chinese humor multi-label dataset showed that HyperGAT model outperforms previous sequence-based (CNN, BiLSTM, FastText) and graph-based (Graph-CNN, TextGCN, Text Level GNN) deep learning models.",

keywords = "Humor recognition, Hypergraph neural networks, Multi-label classification",

author = "Kao, {Hao Chuan} and Hung, {Man Chen} and Lee, {Lung Hao} and Tseng, {Yuen Hsien}",

note = "Publisher Copyright: {\textcopyright} 2021 ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing. All rights reserved.; 33rd Conference on Computational Linguistics and Speech Processing, ROCLING 2021 ; Conference date: 15-10-2021 Through 16-10-2021",

year = "2021",

language = "???core.languages.en_GB???",

series = "ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing",

publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)",

pages = "257--264",

editor = "Lung-Hao Lee and Chia-Hui Chang and Kuan-Yu Chen",

booktitle = "ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing",

}

Kao, HC, Hung, MC, Lee, LH & Tseng, YH 2021, Multi-Label Classification of Chinese Humor Texts Using Hypergraph Attention Networks. 於 L-H Lee, C-H Chang & K-Y Chen (編輯), ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing. ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing, The Association for Computational Linguistics and Chinese Language Processing (ACLCLP), 頁 257-264, 33rd Conference on Computational Linguistics and Speech Processing, ROCLING 2021, Taoyuan, Taiwan, 15/10/21.

Multi-Label Classification of Chinese Humor Texts Using Hypergraph Attention Networks. / Kao, Hao Chuan; Hung, Man Chen; Lee, Lung Hao 等.
ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing. 編輯 / Lung-Hao Lee; Chia-Hui Chang; Kuan-Yu Chen. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP), 2021. p. 257-264 (ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing).

研究成果: 書貢獻/報告類型 › 會議論文篇章 › 同行評審

TY - GEN

T1 - Multi-Label Classification of Chinese Humor Texts Using Hypergraph Attention Networks

AU - Kao, Hao Chuan

AU - Hung, Man Chen

AU - Lee, Lung Hao

AU - Tseng, Yuen Hsien

PY - 2021

Y1 - 2021

N2 - We use Hypergraph Attention Networks (HyperGAT) to recognize multiple labels of Chinese humor texts. We firstly represent a joke as a hypergraph. The sequential hyperedge and semantic hyperedge structures are used to construct hyperedges. Then, attention mechanisms are adopted to aggregate context information embedded in nodes and hyperedges. Finally we use trained HyperGAT to complete the multi-label classification task. Experimental results on the Chinese humor multi-label dataset showed that HyperGAT model outperforms previous sequence-based (CNN, BiLSTM, FastText) and graph-based (Graph-CNN, TextGCN, Text Level GNN) deep learning models.

AB - We use Hypergraph Attention Networks (HyperGAT) to recognize multiple labels of Chinese humor texts. We firstly represent a joke as a hypergraph. The sequential hyperedge and semantic hyperedge structures are used to construct hyperedges. Then, attention mechanisms are adopted to aggregate context information embedded in nodes and hyperedges. Finally we use trained HyperGAT to complete the multi-label classification task. Experimental results on the Chinese humor multi-label dataset showed that HyperGAT model outperforms previous sequence-based (CNN, BiLSTM, FastText) and graph-based (Graph-CNN, TextGCN, Text Level GNN) deep learning models.

KW - Humor recognition

KW - Hypergraph neural networks

KW - Multi-label classification

UR - http://www.scopus.com/inward/record.url?scp=85127449413&partnerID=8YFLogxK

M3 - 會議論文篇章

AN - SCOPUS:85127449413

T3 - ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing

SP - 257

EP - 264

BT - ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing

A2 - Lee, Lung-Hao

A2 - Chang, Chia-Hui

A2 - Chen, Kuan-Yu

PB - The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)

T2 - 33rd Conference on Computational Linguistics and Speech Processing, ROCLING 2021

Y2 - 15 October 2021 through 16 October 2021

ER -

Kao HC, Hung MC, Lee LH, Tseng YH. Multi-Label Classification of Chinese Humor Texts Using Hypergraph Attention Networks. 於 Lee LH, Chang CH, Chen KY, 編輯, ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP). 2021. p. 257-264. (ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing).

Multi-Label Classification of Chinese Humor Texts Using Hypergraph Attention Networks

摘要

出版系列

???event.eventtypes.event.conference???

指紋

專案

中文醫療健康照護知識庫建置與應用(2/3)

引用此