Intention-Based Segmentation: Human Reliability and Correlation with Linguistic Cues


Based on an empirical study of a corpus of spoken narratives, we show that human subjects can reliably perform linear segmentation of discourse, using communicative purpose as their criterion. The significant agreement among subjects leads us to conclude that linear segmentation is feasible for automation. We present a method for evaluating automated… (More)


Figures and Tables

Sorry, we couldn't extract any figures or tables for this paper.


Citations per Year

155 Citations

Semantic Scholar estimates that this publication has 155 citations based on the available data.

See our FAQ for additional information.

Slides referencing similar topics