TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Unsupervised Dependency Parsing	Penn Treebank	Iterative reranking	UAS	66.2	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/unsupervised-dependency-parsing-lets-use/unsupervised-dependency-parsing-on-penn)](https://paperswithcode.com/sota/unsupervised-dependency-parsing-on-penn?p=unsupervised-dependency-parsing-lets-use)`

Unsupervised Dependency Parsing: Let's Use Supervised Parsers

HLT 2015 · Phong Le, Willem Zuidema ·

We present a self-training approach to unsupervised dependency parsing that reuses existing supervised and unsupervised parsing algorithms. Our approach, called `iterated reranking' (IR), starts with dependency trees generated by an unsupervised parser, and iteratively improves these trees using the richer probability models used in supervised parsing that are in turn trained on these trees. Our system achieves 1.8% accuracy higher than the state-of-the-part parser of Spitkovsky et al. (2013) on the WSJ corpus.