We propose a self-supervised word-segmentation technique for Chinese information retrieval. This method combines the advantages of traditional dictionary based approaches with cha...
Fuchun Peng, Xiangji Huang, Dale Schuurmans, Nick ...
In order to become an effective complement to traditional Web-scale text-based image retrieval solutions, content-based image retrieval must address scalability and efficiency iss...
The THOMAS system is designed to make legislative information available to the general public over the Internet, and can be regarded as a prototypeof a government digitallibrary. ...
In this work, we present a system for categorizing photographs based on the text of their captions. The system has been developed as a part of the system CODI, an e-commerce applic...
The global information service in the Internet is a heterogeneous and rapidly evolving environment. Constantly, new information services are added, others are modified, removed or...