Visualization of relational text information for biomedical knowledge discovery

Lexical Navigation provides users with a convenient technique for moving between related documents and terms within a collection without ever having to formulate an exact query to retrieve these related entities. It consists of a visual interface client and an index file . We discuss the algorithms we used to construct unnamed and named relations and the Java libraries we have developed. Many researchers have attempted to find relations in the Biomedical domain using strategies for recognizing protein and gene names, for example. By contrast, our strategy is to find major noun and verb phrases of all types and compute relations by recurring proximity. We then can apply biomedical term recognition as a filter against the relations we discover. Our graphical display of the computed relations can be launched and used without reference to a database, and our XML data representation provides a portable way for other workers to access and visualize the data we have extracted.