English

A PDTB-Styled End-to-End Discourse Parser

Computation and Language 2016-08-30 v1

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.

Keywords

Cite

@article{arxiv.1011.0835,
  title  = {A PDTB-Styled End-to-End Discourse Parser},
  author = {Ziheng Lin and Hwee Tou Ng and Min-Yen Kan},
  journal= {arXiv preprint arXiv:1011.0835},
  year   = {2016}
}

Comments

15 pages, 5 figures, 7 tables

R2 v1 2026-06-21T16:38:16.462Z