Computer Science – Computation and Language
Scientific paper
2010-11-03
Computer Science
Computation and Language
15 pages, 5 figures, 7 tables
Scientific paper
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.
Kan Min-Yen
Lin Ziheng
Ng Hwee Tou
No associations
LandOfFree
A PDTB-Styled End-to-End Discourse Parser does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with A PDTB-Styled End-to-End Discourse Parser, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A PDTB-Styled End-to-End Discourse Parser will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-602957