@InProceedings{morey-muller-asher:2017:EMNLP2017,
  author    = {Morey, Mathieu  and  Muller, Philippe  and  Asher, Nicholas},
  title     = {How much progress have we made on RST discourse parsing? A replication study of recent results on the RST-DT},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {1319--1324},
  abstract  = {This article evaluates purported progress over the past years in RST discourse
	parsing.
	Several studies report a relative error reduction of 24 to 51\% on all metrics
	that authors attribute to the introduction of distributed representations of
	discourse units.
	We replicate the standard evaluation of 9 parsers, 5 of which use distributed
	representations, from 8 studies published between 2013 and 2017, using their
	predictions on the test set of the RST-DT.
	Our main finding is that most recently reported increases in RST discourse
	parser performance are an artefact of differences in implementations of the
	evaluation procedure.
	We evaluate all these parsers with the standard Parseval procedure to provide a
	more accurate picture of the actual RST discourse parsers performance in
	standard evaluation settings.
	Under this more stringent procedure, the gains attributable to distributed
	representations represent at most a 16\% relative error reduction on
	fully-labelled structures.},
  url       = {https://www.aclweb.org/anthology/D17-1136}
}