A hierarchical pointer-network decoder that conditions on parent and sibling states improves discourse parsing relation F1 to 82.77 and gives marginal dependency parsing gains.
A Unified Linear-Time Framework for Sentence-Level Discourse Parsing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose an efficient neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory (RST). Our framework comprises a discourse segmenter to identify the elementary discourse units (EDU) in a text, and a discourse parser that constructs a discourse tree in a top-down fashion. Both the segmenter and the parser are based on Pointer Networks and operate in linear time. Our segmenter yields an $F_1$ score of 95.4, and our parser achieves an $F_1$ score of 81.7 on the aggregated labeled (relation) metric, surpassing previous approaches by a good margin and approaching human agreement on both tasks (98.3 and 83.0 $F_1$).
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hierarchical Pointer Net Parsing
A hierarchical pointer-network decoder that conditions on parent and sibling states improves discourse parsing relation F1 to 82.77 and gives marginal dependency parsing gains.