In this talk we introduce a novel framework for representing and
measuring local coherence. Central to this approach is the entity grid
representation of discourse which captures patterns of entity
distribution in a text. Inspired by Centering Theory, our algorithm
automatically abstracts a text into a set of entity transition
sequences and records distributional, syntactic, and referential
information about discourse entities. We re-conceptualize coherence
assessment as a learning task and show that our entity-based
representation is well-suited for ranking-based generation and text
classification tasks. Using the proposed representation, we achieve
good performance on text ordering, summary coherence evaluation, and
readability assessment.
(This talk reports joint work with Regina Barzilay.)