Exploiting Event Semantics to Parse the Rhetorical Structure of Natural Language Text

Previous work on discourse parsing has mostly relied on surface syntactic and lexical features; the use of semantics is limited to shallow semantics. The goal of this thesis is to exploit event semantics in order to build discourse parse trees (DPT) based on informational rhetorical relations. Our work employs an Inductive Logic Programming (ILP) based rhetorical relation classifier, a Neural Network based discourse segmenter, a bottom-up sentence level discourse parser and a shift-reduce document level discourse parser.

• Type: Conference
• Year: 2007
• Where: NAACL
• Authors: Rajen Subba
• Keywords: Computational Linguistics, Discourse, Discourse Parse Trees, Level Discourse Parser, NAACL 2007