Multi-Task Linear Dependency Modeling for drug-related webpages classification
- Resource Type
- Conference
- Authors
- Hu, Ruiguang; Hao, Mengxi; Jin, Songzhi; Wang, Hao; Gao, Shibo; Xiao, Liping
- Source
- 2017 20th International Conference on Information Fusion (Fusion) Information Fusion (Fusion), 2017 20th International Conference on. :1-7 Jul, 2017
- Subject
- Aerospace
Communication, Networking and Broadcast Technologies
Robotics and Control Systems
Signal Processing and Analysis
Metadata
Web pages
Semantics
Training
Optimization
Linear programming
Tools
webpages classification
information fusion
Multi-Task Linear Dependency Modeling
- Language
In this paper, Multi-Task Linear Dependency Modeling is proposed to distinguish drug-related webpages that contain lots of images and text. Linear Dependency Modeling exploits semantic relations between images features and text features, and Multi-Task Learning takes advantage of metadata of webpages. Meaningful information of webpages can be made use of fully to improve classification accuracy. Experimental results show that Multi-Task Linear Dependency Modeling outperforms existing decision level and feature level combination methods and achieves the best performance.