Abstract
This paper presents a joint model designed to measure local text coherence that uses Rhetorical Structure Theory (RST) and entity grids. The purpose is to learn patterns of entity distribution in texts by considering entity transition sequences and organizational/discourse information using RST relations in order to create a predictive model that is able to distinguish coherent from incoherent texts. In an evaluation with newspaper texts, the proposed model outperformed other methods in the area.
Full Text
Paper version not known (
Free)
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call