Understanding and communication

The explosion of digital documents on the Internet and in the workplace has led to an increasing need for computer systems that help us not only manage the documents but also manage our understanding of these documents and their relationships. These digital documents include speech documents, and video and images as well as text documents in digital form. This minitrack focuses on how one gains an understanding of a digital document and how that information is communicated. It encompasses retrieval and text analysis methods, including summarization, catergorization, genre theory and detection, Web navigation and visualzation methods that increase understanding of document content and genre. This is the second year of this minitrack which is the result of merging two previous successful minitracks, Understanding and Visualization and Genre in Digital Documents. As such, there are continuing themes from both of the previous minitracks and from last year’s successful minitrack. This year there are two sessions. The first session has papers by Boongoen et al. and by Rehm. Both these papers attempt to “understand” documents but from very different approaches. Boongoen uses a network of agents and a natural language approach to extract knowledge from textual sources. The process is evolutionary in nature in that context gained from one document is used to help interpret the next document. Rehm’s approach is to identify the Web genre of documents. His approach is to view a genre as consisting of a set of sub-genres which can then be automatically identified and extracted from the main genre.