KnowledgeSea is a tool that helps you locate materials relevant to C programming.

Relevant concepts from class lectures and several Web-based tutorials and textbooks are identified and clustered together on a knowledge map using a neural network technology. You can find the specific and related information that you need in one area.

» Project Page

Having reference librarians or human intermediaries in the information retrieval process is one of the big successful stories in the development of libraries and library science. However, with widely use of Internet and the Web, more and more searches are performed without the help of human intermediaries. The goal of the SIM project is to transform the knowledge people developed for reference process into modern automatic retrieval process, and design a retrieval system that would be a useful assistant when working with librarians, and a smart automatic intermediary when acting alone.

This project focuses on adaptive navigation support and adaptive visualization in order to provide students with personalized information access to variety of educational resources such as tutorials, electronic textbooks, subject overviews, and so forth. It helps them to find, organize, and use these resources that match their individual goals, interests, and current knowledge.

» Project Page

Even though the advancement of computer and network technology makes it possible that people can access information globally, our such abilities are still dragged down by the fact that most of us lack of proficiency in foreign languages. Research on Cross-Language Information Retrieval (CLIR) helps developing algorithms for identifying relevance information in foreign languages, but many more difficult research problems are to be solved before a useful interactive cross-language information access system can be delivered. The ICLIA research project aims at attacking those problems, and developing tools based on natural language processing techniques to facilitate people to access information regardless of languages, and eventually to develop an efficient, user friendly cross-language information access system.

With the Web as the document collection having vast amount of information for almost every possible topic, the key for the success of a retrieval process is not to identify the relevant information, but to make the relevant information easy accessible to the user. HARD project tries to address this problem by inviting user in the loop. Our research interests in this project are mainly concentrated on using the HARD framework to explore various means to interact with users during the search process, and identify chunks of text (called passages) rather than the whole documents to satisfy users' information need.

Controlled vocabularies offer a consistent means for indexing and retrieving documents in a defined domain. The PSS thesaurus will be revised and expanded in a Web-based collaboratory environment and will serve as the foundation for a new Web portal document repository to be used by the USIP, U.N., World Bank and other affiliated organizations.

Vivisimo is a cluster-based Web search engine that dynamically produces a cluster tree to organize Web search results. A transaction log analysis was conducted to determine characteristics of user interaction with Vivisimo and patterns of cluster use.

Visualization tools offer potential in assisting Web users to select useful items from search results. This study explores the user similarity selection of Web search output in comparison to system generated sets using a Web-based visualization tool, TouchGraph.

Usability research has shown that in a side-by-side comparison, participants often favor a text-based system to that of a visualization interface. Morse et al. have introduced a new testing model which divorces the interface representation from the mechanics of using the system. This investigation builds on components of the BASSTEP methodology to compare participant evaluations of similarity selections using paper-based representations of TouchGraph and Google output.