Meta-learning of Text Classification Tasks

被引：3

作者：

Madrid, Jorge G. ^{[1
]}

Jair Escalante, Hugo ^{[1
,2
]}

机构：

[1] Inst Nacl Astrofis Opt & Electr, Dept Comp Sci, Cholula 72840, Pue, Mexico

[2] IPN, Ctr Invest & Estudios Avanzados, Dept Comp Sci, Mexico City 07360, DF, Mexico

来源：

PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS (CIARP 2019) | 2019年 / 11896卷

关键词：

Meta-learning; Text classification; Meta-features;

D O I：

10.1007/978-3-030-33904-3_10

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A text mining characterization is proposed consisting of a set of meta-features, unlike previous meta-learning approaches, some of them are extracted directly from raw text. Such novel description is useful for comparing text mining tasks and study their differences. The problem of determining the task associated to a text classification dataset is introduced and approached with our characterization. Experimental results on a set of 81 corpora show that the proposed meta-features indeed allow to recognize tasks with acceptable performance using only a few meta-features.

引用

页码：107 / 119

页数：13

共 50 条

[11] Meta-learning from Tasks with Heterogeneous Attribute Spaces
Iwata, Tomoharu
Kumagai, Atsutoshi
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
[12] What Matters For Meta-Learning Vision Regression Tasks?
Gao, Ning
Ziesche, Hanna
Ngo Anh Vien
Volpp, Michael
Neumann, Gerhard
[J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 14756 - 14766
[13] How to Distribute Data across Tasks for Meta-Learning?
Cioba, Alexandru
Bromberg, Michael
Wang, Qian
Niyogi, Ritwik
Batzolis, Georgios
Garcia, Jezabel
Shiu, Da-shan
Bernacchia, Alberto
[J]. THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 6394 - 6401
[14] Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks
Bansal, Trapit
Jha, Rishikesh
Munkhdalai, Tsendsuren
McCallum, Andrew
[J]. PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 522 - 534
[15] Target unbiased meta-learning for graph classification
Li, Ming
Zhu, Shuo
Li, Chunxu
Zhao, Wencang
[J]. JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING, 2021, 8 (05) : 1355 - 1366
[16] Automatic Modulation Classification via Meta-Learning
Hao, Xiaoyang
Feng, Zhixi
Yang, Shuyuan
Wang, Min
Jiao, Licheng
[J]. IEEE INTERNET OF THINGS JOURNAL, 2023, 10 (14) : 12276 - 12292
[17] Improving Meta-Learning Classification with Prototype Enhancement
Pan, Xiaohang
Li, Fanzhang
Liu, Li
[J]. 2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
[18] Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation
Zhao, Yingxiu
Tian, Zhiliang
Yao, Huaxiu
Zheng, Yinhe
Lee, Dongkyu
Song, Yiping
Sun, Jian
Zhang, Nevin L.
[J]. PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 583 - 595
[19] META-LEARNING FOR EEG MOTOR IMAGERY CLASSIFICATION
Yu, Jian
Duan, Lili
Ji, Hongfei
Li, Jie
Pang, Zilong
[J]. COMPUTING AND INFORMATICS, 2024, 43 (03) : 735 - 755
[20] Automated imbalanced classification via meta-learning
Moniz, Nuno
Cerqueira, Vitor
[J]. Expert Systems with Applications, 2021, 178

← 1 2 3 4 5 →