Abstractive Dialogue Summarization Based on Dynamic Pattern Exploiting Training

Zhanyi Chen; Changqun Li; Linlin Wang; Liang He

doi:10.1109/IJCNN55064.2022.9892323

Abstractive Dialogue Summarization Based on Dynamic Pattern Exploiting Training

Zhanyi Chen
, Changqun Li
, Linlin Wang^*
, Liang He

^*Corresponding author for this work

School of Computer Science and Technology

East China Normal University

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

Abstract

Pre-trained language models (PLMs) have shown remarkable performance in natural language processing tasks, whereas these approaches often require a massive amount of data. Due to the lack of sufficient training instances, it is challenging for existing PLMs to achieve good results on dialogue summarization. In this paper, we propose DynamicPET, a pattern-exploiting training (PET) based method for abstractive dialogue summarization, which leverages the recent prompt learning paradigm to boost the performance of PLMs. In contrast to PET, our method does not rely on any task-specific unlabeled data, but obtains strong performance on two dialogue summarization datasets, especially in the few-shot scenarios.

Original language	English
Title of host publication	2022 International Joint Conference on Neural Networks, IJCNN 2022 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728186719
DOIs	https://doi.org/10.1109/IJCNN55064.2022.9892323
State	Published - 2022
Event	2022 International Joint Conference on Neural Networks, IJCNN 2022 - Padua, Italy Duration: 18 Jul 2022 → 23 Jul 2022

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
ISSN (Print)	2161-4393
ISSN (Electronic)	2161-4407

Conference

Conference	2022 International Joint Conference on Neural Networks, IJCNN 2022
Country/Territory	Italy
City	Padua
Period	18/07/22 → 23/07/22

Keywords

Dialogue summarization
Pre-trained Language Model
Prompt Learning

Access to Document

10.1109/IJCNN55064.2022.9892323

Cite this

Chen, Z., Li, C., Wang, L., & He, L. (2022). Abstractive Dialogue Summarization Based on Dynamic Pattern Exploiting Training. In 2022 International Joint Conference on Neural Networks, IJCNN 2022 - Proceedings (Proceedings of the International Joint Conference on Neural Networks). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN55064.2022.9892323

@inproceedings{ef1c906df13148198053af1515b454fa,

title = "Abstractive Dialogue Summarization Based on Dynamic Pattern Exploiting Training",

abstract = "Pre-trained language models (PLMs) have shown remarkable performance in natural language processing tasks, whereas these approaches often require a massive amount of data. Due to the lack of sufficient training instances, it is challenging for existing PLMs to achieve good results on dialogue summarization. In this paper, we propose DynamicPET, a pattern-exploiting training (PET) based method for abstractive dialogue summarization, which leverages the recent prompt learning paradigm to boost the performance of PLMs. In contrast to PET, our method does not rely on any task-specific unlabeled data, but obtains strong performance on two dialogue summarization datasets, especially in the few-shot scenarios.",

keywords = "Dialogue summarization, Pre-trained Language Model, Prompt Learning",

author = "Zhanyi Chen and Changqun Li and Linlin Wang and Liang He",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 International Joint Conference on Neural Networks, IJCNN 2022 ; Conference date: 18-07-2022 Through 23-07-2022",

year = "2022",

doi = "10.1109/IJCNN55064.2022.9892323",

language = "英语",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 International Joint Conference on Neural Networks, IJCNN 2022 - Proceedings",

address = "美国",

}

Chen, Z, Li, C, Wang, L & He, L 2022, Abstractive Dialogue Summarization Based on Dynamic Pattern Exploiting Training. in 2022 International Joint Conference on Neural Networks, IJCNN 2022 - Proceedings. Proceedings of the International Joint Conference on Neural Networks, Institute of Electrical and Electronics Engineers Inc., 2022 International Joint Conference on Neural Networks, IJCNN 2022, Padua, Italy, 18/07/22. https://doi.org/10.1109/IJCNN55064.2022.9892323

Abstractive Dialogue Summarization Based on Dynamic Pattern Exploiting Training. / Chen, Zhanyi; Li, Changqun; Wang, Linlin et al.
2022 International Joint Conference on Neural Networks, IJCNN 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. (Proceedings of the International Joint Conference on Neural Networks).

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

TY - GEN

T1 - Abstractive Dialogue Summarization Based on Dynamic Pattern Exploiting Training

AU - Chen, Zhanyi

AU - Li, Changqun

AU - Wang, Linlin

AU - He, Liang

PY - 2022

Y1 - 2022

N2 - Pre-trained language models (PLMs) have shown remarkable performance in natural language processing tasks, whereas these approaches often require a massive amount of data. Due to the lack of sufficient training instances, it is challenging for existing PLMs to achieve good results on dialogue summarization. In this paper, we propose DynamicPET, a pattern-exploiting training (PET) based method for abstractive dialogue summarization, which leverages the recent prompt learning paradigm to boost the performance of PLMs. In contrast to PET, our method does not rely on any task-specific unlabeled data, but obtains strong performance on two dialogue summarization datasets, especially in the few-shot scenarios.

AB - Pre-trained language models (PLMs) have shown remarkable performance in natural language processing tasks, whereas these approaches often require a massive amount of data. Due to the lack of sufficient training instances, it is challenging for existing PLMs to achieve good results on dialogue summarization. In this paper, we propose DynamicPET, a pattern-exploiting training (PET) based method for abstractive dialogue summarization, which leverages the recent prompt learning paradigm to boost the performance of PLMs. In contrast to PET, our method does not rely on any task-specific unlabeled data, but obtains strong performance on two dialogue summarization datasets, especially in the few-shot scenarios.

KW - Dialogue summarization

KW - Pre-trained Language Model

KW - Prompt Learning

UR - https://www.scopus.com/pages/publications/85140710753

U2 - 10.1109/IJCNN55064.2022.9892323

DO - 10.1109/IJCNN55064.2022.9892323

M3 - 会议稿件

AN - SCOPUS:85140710753

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2022 International Joint Conference on Neural Networks, IJCNN 2022 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 International Joint Conference on Neural Networks, IJCNN 2022

Y2 - 18 July 2022 through 23 July 2022

ER -

Abstractive Dialogue Summarization Based on Dynamic Pattern Exploiting Training

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this