We present a methodology for automatically constructing structural hyperlinks for navigation and retrieval in large corpora. A structural hyperlink connects components of a document that have specified structural properties with word-based content similarity. Our approach enables queries that may be posed in terms of keywords, as well as structural segments such as definitions, figures, etc.

Previous research has indicated that when a polysemous word appears two or more times in a discourse, it is extremely likely that they will all share the same sense [Gale et al. 92]. However, those results were based on a coarse-grained distinction between senses (e.g, sentence in the sense of a ‘prison sentence’ vs. a ‘grammatical sentence’). We report on an analysis of multiple senses within ...