Generative Adversarial Networks based on Mixed-Attentions for Citation Intent Classification in Scientific Publications

Yuh Shyang Wang; Chao Yi Chen; Lung Hao Lee

Generative Adversarial Networks based on Mixed-Attentions for Citation Intent Classification in Scientific Publications

Yuh Shyang Wang, Chao Yi Chen, Lung Hao Lee

Department of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We propose the mixed-attention-based Generative Adversarial Network (named maGAN), and apply it for citation intent classification in scientific publication. We select domain-specific training data, propose a mixed attention mechanism, and employ generative adversarial network architecture for pre-training language model and fine-tuning to the downstream multi-class classification task. Experiments were conducted on the SciCite datasets to compare model performance. Our proposed maGAN model achieved the best Macro-F1 of 0.8532.

Original language	English
Title of host publication	ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing
Editors	Lung-Hao Lee, Chia-Hui Chang, Kuan-Yu Chen
Publisher	The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
Pages	280-285
Number of pages	6
ISBN (Electronic)	9789869576949
State	Published - 2021
Event	33rd Conference on Computational Linguistics and Speech Processing, ROCLING 2021 - Taoyuan, Taiwan Duration: 15 Oct 2021 → 16 Oct 2021

Publication series

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

Conference

Conference	33rd Conference on Computational Linguistics and Speech Processing, ROCLING 2021
Country/Territory	Taiwan
City	Taoyuan
Period	15/10/21 → 16/10/21

Keywords

Attentions
Citation intents
Pretrained language models
Scientific publications

Chinese Knowledge Base Construction and Applications for Medical Healthcare Domain(2/3)
Lee, L.-H. (PI)
1/05/20 → 30/04/21
Project: Research

Cite this

Wang, Y. S., Chen, C. Y., & Lee, L. H. (2021). Generative Adversarial Networks based on Mixed-Attentions for Citation Intent Classification in Scientific Publications. In L.-H. Lee, C.-H. Chang, & K.-Y. Chen (Eds.), ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (pp. 280-285). (ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing). The Association for Computational Linguistics and Chinese Language Processing (ACLCLP).

Wang, Yuh Shyang ; Chen, Chao Yi ; Lee, Lung Hao. / Generative Adversarial Networks based on Mixed-Attentions for Citation Intent Classification in Scientific Publications. ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing. editor / Lung-Hao Lee ; Chia-Hui Chang ; Kuan-Yu Chen. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP), 2021. pp. 280-285 (ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing).

@inproceedings{31a897bc650344fda5c5d5af38e9c321,

title = "Generative Adversarial Networks based on Mixed-Attentions for Citation Intent Classification in Scientific Publications",

abstract = "We propose the mixed-attention-based Generative Adversarial Network (named maGAN), and apply it for citation intent classification in scientific publication. We select domain-specific training data, propose a mixed attention mechanism, and employ generative adversarial network architecture for pre-training language model and fine-tuning to the downstream multi-class classification task. Experiments were conducted on the SciCite datasets to compare model performance. Our proposed maGAN model achieved the best Macro-F1 of 0.8532.",

keywords = "Attentions, Citation intents, Pretrained language models, Scientific publications",

author = "Wang, {Yuh Shyang} and Chen, {Chao Yi} and Lee, {Lung Hao}",

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 = "280--285",

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",

}

Wang, YS, Chen, CY & Lee, LH 2021, Generative Adversarial Networks based on Mixed-Attentions for Citation Intent Classification in Scientific Publications. in L-H Lee, C-H Chang & K-Y Chen (eds), 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), pp. 280-285, 33rd Conference on Computational Linguistics and Speech Processing, ROCLING 2021, Taoyuan, Taiwan, 15/10/21.

Generative Adversarial Networks based on Mixed-Attentions for Citation Intent Classification in Scientific Publications. / Wang, Yuh Shyang; Chen, Chao Yi; Lee, Lung Hao.
ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing. ed. / Lung-Hao Lee; Chia-Hui Chang; Kuan-Yu Chen. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP), 2021. p. 280-285 (ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Generative Adversarial Networks based on Mixed-Attentions for Citation Intent Classification in Scientific Publications

AU - Wang, Yuh Shyang

AU - Chen, Chao Yi

AU - Lee, Lung Hao

PY - 2021

Y1 - 2021

N2 - We propose the mixed-attention-based Generative Adversarial Network (named maGAN), and apply it for citation intent classification in scientific publication. We select domain-specific training data, propose a mixed attention mechanism, and employ generative adversarial network architecture for pre-training language model and fine-tuning to the downstream multi-class classification task. Experiments were conducted on the SciCite datasets to compare model performance. Our proposed maGAN model achieved the best Macro-F1 of 0.8532.

AB - We propose the mixed-attention-based Generative Adversarial Network (named maGAN), and apply it for citation intent classification in scientific publication. We select domain-specific training data, propose a mixed attention mechanism, and employ generative adversarial network architecture for pre-training language model and fine-tuning to the downstream multi-class classification task. Experiments were conducted on the SciCite datasets to compare model performance. Our proposed maGAN model achieved the best Macro-F1 of 0.8532.

KW - Attentions

KW - Citation intents

KW - Pretrained language models

KW - Scientific publications

UR - http://www.scopus.com/inward/record.url?scp=85127430967&partnerID=8YFLogxK

M3 - 會議論文篇章

AN - SCOPUS:85127430967

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

SP - 280

EP - 285

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 -

Wang YS, Chen CY, Lee LH. Generative Adversarial Networks based on Mixed-Attentions for Citation Intent Classification in Scientific Publications. In Lee LH, Chang CH, Chen KY, editors, 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. 280-285. (ROCLING 2021 - Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing).

Generative Adversarial Networks based on Mixed-Attentions for Citation Intent Classification in Scientific Publications

Abstract

Publication series

Conference

Keywords

Fingerprint

Projects

Chinese Knowledge Base Construction and Applications for Medical Healthcare Domain(2/3)

Cite this