2000 character limit reached
A PDTB-Styled End-to-End Discourse Parser (1011.0835v1)
Published 3 Nov 2010 in cs.CL
Abstract: We have developed a full discourse parser in the Penn Discourse Treebank (PDTB) style. Our trained parser first identifies all discourse and non-discourse relations, locates and labels their arguments, and then classifies their relation types. When appropriate, the attribution spans to these relations are also determined. We present a comprehensive evaluation from both component-wise and error-cascading perspectives.