Few-Shot and Prompt Training for Text Classification in German Doctor's Letters

被引：0

作者：

Richter-Pechanski, Phillip ^{[1
,2
,3
,4
]}

Wiesenbach, Philipp ^{[1
,2
,4
]}

Schwa, Dominic M. ^{[2
]}

Kiriakou, Christina ^{[2
]}

He, Mingyang ^{[1
,2
]}

Geis, Nicolas A. ^{[2
,4
]}

Frank, Anette ^{[5
]}

Dieterich, Christoph ^{[1
,2
,3
,4
]}

机构：

[1] Klaus Tschira Inst Computat Cardiol, Heidelberg, Germany

[2] Univ Heidelberg Hosp, Dept Internal Med 3, Heidelberg, Germany

[3] German Ctr Cardiovasc Res DZHK, Partner Site Heidelberg Mannheim, Berlin, Germany

[4] Informat Life, Heidelberg, Germany

[5] Heidelberg Univ, Dept Computat Linguist, Heidelberg, Germany

来源：

CARING IS SHARING-EXPLOITING THE VALUE IN DATA FOR HEALTH AND INNOVATION-PROCEEDINGS OF MIE 2023 | 2023年 / 302卷

关键词：

deep learning; prompting; language models; cardiology;

D O I：

10.3233/SHTI230275

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

To classify sentences in cardiovascular German doctor's letters into eleven section categories, we used pattern-exploiting training, a prompt-based method for text classification in few-shot learning scenarios (20, 50 and 100 instances per class) using language models with various pre-training approaches evaluated on CARDIO:DE, a freely available German clinical routine corpus. Prompting improves results by 5-28% accuracy compared to traditional methods, reducing manual annotation efforts and computational costs in a clinical setting.

引用

页码：819 / 820

页数：2

共 50 条

[21] Investigating Prompt Learning for Chinese Few-Shot Text Classification with Pre-Trained Language Models
Song, Chengyu
Shao, Taihua
Lin, Kejing
Liu, Dengfeng
Wang, Siyuan
Chen, Honghui
APPLIED SCIENCES-BASEL, 2022, 12 (21):
[22] Prompt-Based Graph Convolution Adversarial Meta-Learning for Few-Shot Text Classification
Gong, Ruwei
Qin, Xizhong
Ran, Wensheng
APPLIED SCIENCES-BASEL, 2023, 13 (16):
[23] Mask-guided BERT for few-shot text classification
Liao, Wenxiong
Liu, Zhengliang
Dai, Haixing
Wu, Zihao
Zhang, Yiyang
Huang, Xiaoke
Chen, Yuzhong
Jiang, Xi
Liu, David
Zhu, Dajiang
Li, Sheng
Liu, Wei
Liu, Tianming
Li, Quanzheng
Cai, Hongmin
Li, Xiang
NEUROCOMPUTING, 2024, 610
[24] On Training Instance Selection for Few-Shot Neural Text Generation
Chang, Ernie
Shen, Xiaoyu
Yeh, Hui-Syuan
Demberg, Vera
ACL-IJCNLP 2021: THE 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 2, 2021, : 8 - 13
[25] ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification
Chen, Junfan
Zhang, Richong
Mao, Yongyi
Xu, Jie
THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 10492 - 10500
[26] Mutual Learning Prototype Network for Few-Shot Text Classification
Liu, Jun
Qin, Xiaorui
Tao, Jian
Dong, Hongfei
Li, Xiaoxu
Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications, 2024, 47 (03): : 30 - 35
[27] Knowledge Guided Metric Learning for Few-Shot Text Classification
Sui, Dianbo
Chen, Yubo
Mao, Binjie
Qiu, Delai
Liu, Kang
Zhao, Jun
2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL-HLT 2021), 2021, : 3266 - 3271
[28] Hierarchical Attention Prototypical Networks for Few-Shot Text Classification
Sun, Shengli
Sun, Qingfeng
Zhou, Kevin
Lv, Tengchao
2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 476 - 485
[29] Few-shot Text Classification Method Based on Feature Optimization
Peng, Jing
Huo, Shuquan
JOURNAL OF WEB ENGINEERING, 2023, 22 (03): : 497 - 514
[30] Dynamic Memory Induction Networks for Few-Shot Text Classification
Geng, Ruiying
Li, Binhua
Li, Yongbin
Sun, Jian
Zhu, Xiaodan
58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020), 2020, : 1087 - 1094

← 1 2 3 4 5 →