Relying on the idea that back-of-the-book indexes are traditional devices for navigation through large documents, we have developed a method to build a hypertextual network that h...
Document classification presents difficult challenges due to the sparsity and the high dimensionality of text data, and to the complex semantics of the natural language. The tradi...
Mobile devices such as cell phone, PDA and smart phone have been so popularized that they are to be a necessity for everyday life. These mobile devices can be very useful tools to ...
Previous work on discourse parsing has mostly relied on surface syntactic and lexical features; the use of semantics is limited to shallow semantics. The goal of this thesis is to...