A Real-time Integration Of Concept-based Search and Summarization of Chinese Websites

A Real-time Integration of Concept-based Search and Summarization on Chinese Websites Joe F Zhou and Weiquan Liu lntel China Research Center 100020 Beijing, China ~/oe.f.zhou; louis.liu}@intel.com Abstract This paper introduces an intuitive search environment for casual and novice Chinese users over Internet. The system consists of four components, a concept network, a query reformulation model, a standard search engine, and an automatic summarizer. When the user enters one or more fairly general and vague terms, the search engine returns an initial answer set, and at the same time pipes the query to the concept network that connects thousands of conceptual nodes, each referring to a specific concept for a given domain and pointing to a number of associated conceptual terms. If the concept is located in the network, the related conceptual terms are displayed. The user has the option of using one or more of these specific terms to reformulate the next round of searches. Such search iterations continue until the user' s ultimate information seeking goal is reached. For each search iteration, auto summarizer presents the main theme of the document retrieved and an optional text-to-speech engine can read out the output summary if the user prefers. 1. Introduction Internet is changing the world, and at the same time changing people' s information seeking behaviour. Traditionally, information searchers are trained professionals working in libraries or other special technical or scientific fields. They have developed a variety of techniques and heuristics for addressing information seeking difficulties in the environment typically dominated by Boolean query formula. These Boolean information retrieval systems are normally commercial and non-interactive systems and the searches conducted in such settings are exact-match and set-based retrieval from databases of indexed citations and abstracts of documents (Koenemann and Belkin, 1996). With the dramatic explosion of information sources over Internet, current user population is no longer restricted to' professional searchers. Practically it includes everyone in life. The majority of these users, however, are either casual or novice or both. Casual users, such as browsers of news stories, look for interesting information rather than information relevant to a specific need (Stadnyk and Kass, 1992). Novice users may have a specific information topic, but due to little or no training in search and retrieval, they don' t know how to make best use of the available operators and tools. On the whole, query formulation is one problem facing both types of information users (Turtle, 1994). Internet users all have difficulty in mapping their intent to any logical query structure. They prefer limiting their searches to one or a simple list of terms, while seeking help from the system to guide them to achieve their ultimate information goal. In this paper we introduce an integrated system that combines a standard search system with a query reformulation model, a pre-constructed concept network, an automatic document summarizer, and an optional text-to-speech (TTS) engine. Together, these intelligent components provide intuitive human intelligence to the Chinese users over Internet. The integrated system not only guides and navigates …

Content truncated to 500 words