Download now Free registration required
Collaborative query routing is a new paradigm for web search that treats both, established search engines and other publicly available indices, as intelligent peer agents in a search network. The approach makes it transparent for anyone to build their search engine by integrating established web search services, desktop search, and topical crawling techniques. The challenge is that each of these agents must learn about its environment the existence, knowledge, diversity, reliability, and trustworthiness of other agents. The 6S peer network uses machine learning techniques to learn about the changing query environment. Simple reinforcement learning algorithms are sufficient to detect and exploit semantic locality in the network, resulting in efficient routing and high-quality search results. It has the potential to attract a community of users. This will help in testing its scalability and robustness while improving its usability and effectiveness. It is important to understand how users interact with 6S and how to best keep their experience positive. Additional learning algorithms and number of other IR techniques have to be explored to improve the performance of 6S's adaptive query routing. Investigating extensions to the peer selection algorithm in which a peer would pay attention to the overlap between two neighbors is also required. In developing a collaborative, peer-based search network, one has to think about protecting the system from abuse.
- Format: PDF
- Size: 6564.9 KB