☆ 3.8 Proceedings Paper

Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations

PROCEEDINGS OF THE ACM WEB CONFERENCE 2022 (WWW'22) (2022)

MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information

Yu Zhang et al.

Summary: We study the problem of weakly supervised text classification and propose a method that utilizes metadata to assist in the classification. We model the relationships between documents and metadata using a heterogeneous information network, and use motifs to describe combinations of metadata. Experimental results demonstrate the superior performance of our method on real-world datasets, and further analysis shows the benefit of considering higher-order metadata information in the framework.

WSDM'22: PROCEEDINGS OF THE FIFTEENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING (2022)

添加到收藏夹

Proceedings Paper Computer Science, Information Systems

Discriminative Topic Mining via Category-Name Guided Text Embedding

Yu Meng et al.

WEB CONFERENCE 2020: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2020) (2020)

添加到收藏夹

Proceedings Paper Computer Science, Information Systems

WELDA: Enhancing Topic Models by Incorporating Local Word Context

Stefan Bunk et al.

JCDL'18: PROCEEDINGS OF THE 18TH ACM/IEEE JOINT CONFERENCE ON DIGITAL LIBRARIES (2018)

添加到收藏夹

Proceedings Paper Computer Science, Information Systems

Weakly-Supervised Neural Text Classification

Yu Meng et al.

CIKM'18: PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT (2018)

添加到收藏夹

Article Statistics & Probability

A CORRELATED TOPIC MODEL OF SCIENCE

David M. Blei et al.

ANNALS OF APPLIED STATISTICS (2007)

添加到收藏夹

Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations

相关参考文献

MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information

Discriminative Topic Mining via Category-Name Guided Text Embedding

WELDA: Enhancing Topic Models by Incorporating Local Word Context

Weakly-Supervised Neural Text Classification

A CORRELATED TOPIC MODEL OF SCIENCE

导出引文

分享论文