Sentence level discourse parsing using syntactic and lexical information

Abstract

We introduce two probabilistic models that can be used to identify elementary discourse units and build sentence-level discourse parse trees. The models use syntactic and lexical features. A discourse parsing algorithm that implements these models derives discourse parse trees with an error reduction of 18.8% over a state-ofthe-art decision-based discourse parser. A set of empirical evaluations shows that our discourse parsing model is sophisticated enough to yield discourse trees at an accuracy level that matches near-human levels of performance.