Knowledge-level management of Web information

Abstract

We present a knowledge-rich software agent, ContextExplicator, which mediates between the Web and the user's information or knowledge needs. It provides a method for incremental knowledge-level management (i.e., knowledge discovery, acquisition and representation) for heterogeneous information in the Web. In ContextExplicator, the incremental knowledge management works through iterative negotiations with the human user: 1. Automatic Word-Sense1 Disambiguation and Induction. General knowledge (e.g., from a lexicon) and previously discovered knowledge support the sense-disambiguation & sense-induction of a word in the given documents, resulting in an improved and refined organization of previously discovered knowledge, 2. Interactive Specialization of Query Criteria. At a given moment, the user can reduce certain semantic ambiguities of previously discovered knowledge by selecting one of the context-words which are suggested by ContextExplicator to discriminate between sets of retrieved documents. The selected context-word is also used to direct the discovery of new knowledge in the given documents, and 3. Visualization of the Discovered Knowledge. The discovered knowledge is represented in a conceptual lattice. Each lattice-node represents a single word-sense or a conjunction of senses of multiple words. To each node the respectively identified documents are associated. Each web-document is multi-classified into relevant word-sense clusters (lattice nodes), according to the occurrences of specific word-senses in the respective web-document. As a conceptual lattice allows the user to navigate the word-sense clusters and the classified web-documents with multi-level abstractions (i.e., super-/sub-lattice nodes), it provides a flexible scheme for managing knowledge and web-documents in a scalable way. © Springer-Verlag Berlin Heidelberg 2005.