Discusses natural language processing and proposes a novel approach to automatic text segmentation using heterogeneous linguistic knowledge and cluster algorithms. Represents the diversity of textual relations in a discourse network in order to analyze the linguistic bonds and determine the degree of coherence that a text may exhibit. (Author/LRW)

Investigates whether information abstracts reporting on empirical work possess a predictable discourse-level structure and whether there are lexical clues revealing this structure. Results support the presence of a detectable structure in the text-type of empirical abstracts, which may be of use in a variety of text-based information processing…

Presents an algorithm for use in natural language document retrieval systems which automatically determines if the conjunction "and" in a statement representing an information need should be translated into a Boolean "and" or "or." The results of an experiment that used the algorithm are reported, and further research is suggested. (CLB)