ESURF, a simple random forest with lexical and character n-gram features, reaches state-of-the-art EDU segmentation on RST-DT and modestly improves RST parsing.
RST Parsing from Scratch
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We introduce a novel top-down end-to-end formulation of document-level discourse parsing in the Rhetorical Structure Theory (RST) framework. In this formulation, we consider discourse parsing as a sequence of splitting decisions at token boundaries and use a seq2seq network to model the splitting decisions. Our framework facilitates discourse parsing from scratch without requiring discourse segmentation as a prerequisite; rather, it yields segmentation as part of the parsing process. Our unified parsing model adopts a beam search to decode the best tree structure by searching through a space of high-scoring trees. With extensive experiments on the standard English RST discourse treebank, we demonstrate that our parser outperforms existing methods by a good margin in both end-to-end parsing and parsing with gold segmentation. More importantly, it does so without using any handcrafted features, making it faster and easily adaptable to new languages and domains.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ESURF: Simple and Effective EDU Segmentation
ESURF, a simple random forest with lexical and character n-gram features, reaches state-of-the-art EDU segmentation on RST-DT and modestly improves RST parsing.